About artificial intelligence projects, I believe that we have seen or used a lot, but most of them look very “high”, let a person feel to master them like learning the dragon slaying skills. In fact, there are many ai projects that are useful and interesting to use. Here are 12 open source AI projects with unique features.

Scikit-learn for Multiple clustering

A Python module for machine learning based on Scipy features a variety of classification, regression, and clustering algorithms including support vector machines, logistic regression, Naive Bayes Classifier, Random forest, Gradient Boosting, Clustering, and DBSCAN. Python numerical and Scientific Libraries Numpy and Scipy have also been designed

Project Address:

https://link.zhihu.com/?target=http%3A//www.github.com/scikit-learn/scikit-learn

A high efficiency Ramp

Why you should check it out: Ramp is a library for developing solutions to speed prototyping in machine learning in Python. Ramp is a lightweight pluggable framework for pandas based machine learning. Its existing Python machine learning and statistics tools (sciKit-learn, RPY2, etc.), Ramp, provide a simple declarative syntax exploration to implement algorithms and transformations quickly and efficiently.

The project address

http://www.github.com/kvh/ramp

Three,STYLE2PAINTS: Powerful AI for paints

Recommended reason: The new generation of powerful line draft color AI, can be uploaded according to the user’s custom color line draft color. The project provides online access to the site, which is very easy to use.

The project address

https://www.oschina.net/p/style2paints

Four,SerpentAI: A Python based learning framework for teaching AI to play games

Why you should check it out: SerpentAI aims to provide a valuable tool for machine learning and AI research. But at the same time, it is also very interesting for lovers.

Serpent.ai contains a number of support modules that provide solutions to scenarios that are often encountered when using games as a development environment, as well as CLI tools to accelerate development. Supports Linux, Windows, and MacOS.

SerpentAI is a Game Agent framework (ps: machine players are often called Agents in order to distinguish between players in man-machine battles) that is simple and powerful. It can turn any Game into a Sandbox environment written in Python in which developers can experiment with the Game Agent, using Python code that developers are very familiar with.

The project address

https://www.oschina.net/p/serpentai

Five,Synaptic. Js: Neural network library for browsers

Why you should check it out: Synaptic. Js is a JavaScript neural network library for Node.js and browsers that can build and train basically any type of first or even second order neural network.

Four classical neural network algorithms are built into the project: Multilayer perceptrons, Multilayer long-short Term memory networks, Liquid State machines Machine), Hopfield neural network. With Synaptic. Js, you can easily test and compare the performance of different architectures.

The project address

https://www.oschina.net/p/serpentai

Vi.Snake-AI: Artificial intelligence for Snake games

Why you should check it out: An AI for snake game written in C/C++. Using shortest path, longest path, artificial intelligence algorithm.

The AI’s goal is to get the snake to eat as much food as possible until the entire map is full.

Demo

The project address

https://www.oschina.net/p/snake-ai

Seven,Uncaptcha: AI algorithm for cracking reCAPTCHA systems

Why we recommend it: unCAPTCHA beats the Google reCAPTCHA system 85% of the time. It relies on audio captcha attacks – using browser automation software to parse the necessary elements and recognize speech numbers, and deliver those numbers programmatically, ultimately successfully tricking the target website.

The project address

https://www.oschina.net/p/uncaptcha

Eight,Sockeye: Neural machine translation framework based on Apache MXNet

Why you should check it out: Sockeye is a fast and extensible deep learning library based on Apache MXNet.

The Sockeye codebase has a unique advantage from MXNet. For example, Sockeye combines declarative and imperative programming styles through symbolic and imperative MXNet apis; It can also train models on multiple Gpus in parallel.

Sockeye implements the current best sequence-to-sequence model on MXNet. It also provides appropriate defaults for all sequence-to-sequence model hyperparameters. For optimization, there is no need to worry about stopping criteria, metric tracking, or weight initialization. You can simply run the provided training command line interface (CLI) and easily change the underlying model architecture.

The project address

https://www.oschina.net/p/sockeye

Eight,CycleGAN: Generates adversarial network image processing tools

Why you should check it out: It’s a powerful tool that not only “restores” a painting to a photo (sort of a “backfilter”), but also turns summer into winter or a regular horse into a zebra.

Unlike other AI paintings, CycleGAN’s team tried to build a two-way algorithm that could be converted in both directions without losing information. In CycleGAN, the details of the photos are required to be completely preserved, and the researchers hope to be able to input an image into CycleGAN and transform it many times (photo → painting → photo → painting → photo), and eventually get the same or similar image as the original one.

The project address

https://www.oschina.net/p/cyclegan

Ten,Deeplearn.js: hardware-accelerated machine learning JavaScript library

Deeplearn.js is an open source JavaScript library from Google that can be used for machine intelligence and accelerate WebGL. Deeplearn.js runs completely in the browser, requires no installation, and requires no back-end processing.

Deeplearn.js provides efficient machine learning building blocks that allow us to train neural networks in a browser or run pre-trained models in inferential mode. It provides an API for building a differentiable data flow graph, as well as a series of straightforward mathematical functions.

While machine learning libraries on browsers have existed for years (e.g. Andrej Karpathy’s ConvnetJS), they are limited by JavaScript speed or are limited to reasoning and cannot be used for training (e.g. TensorFire). In contrast, deeplearn.js achieves significant acceleration by taking advantage of WebGL’s ability to perform computations on gpus and perform full backpropagation.

The project address

https://www.oschina.net/p/deeplearn-js

Eleven,TensorFire: A webGL-based browser-side neural network framework

Why you should check it out: TensorFire is a WebGL-based neural network framework that runs in a browser. Applications written using TensorFire can implement cutting-edge deep learning algorithms while running directly in modern browsers without any installation or configuration.

TensorFire is nearly a hundredfold faster than previous neural network frameworks in some browsers, even matching the performance of code running on native cpus.

Developers can also use the underlying interfaces provided by TensorFire for other high-performance computing, such as PageRank, cellular automata simulation, image conversion and filtering, and more.

The project address

https://www.oschina.net/p/tensorfire

Twelve,Php-ml: PHP machine learning library

We all know that Python or C++ offer more machine learning libraries, but most of them are complex enough to make configuration a pain for beginners. Php-ml machine learning library although there is no particularly sophisticated algorithms, but it has the most basic machine learning, classification and other algorithms, small projects or small companies to do some simple data analysis, prediction and so on enough.

Php-ml is a machine learning library written in PHP. It also includes algorithm, cross validation, neural network, preprocessing, feature extraction and so on.

The project address

https://www.oschina.net/p/php-ml

To read more

Android advanced FFmpeg video playback

11 great Android open Source projects

11 Open Source Projects Android Developers can’t Miss

NDK project actual combat – high imitation 360 mobile phone assistant uninstall monitoring

Believe in yourself, nothing can not be done, only unexpected, if you feel this article is helpful to you, welcome to pay attention to. CodeGoogler’s AI projects, I’m sure you’ve all seen or used a lot of them, but most of them look “awesome” and feel like mastering them is like slaying a dragon. In fact, there are many ai projects that are useful and interesting to use. Here are 12 open source AI projects with unique features.

Scikit-learn for Multiple clustering

A Python module for machine learning based on Scipy features a variety of classification, regression, and clustering algorithms including support vector machines, logistic regression, Naive Bayes Classifier, Random forest, Gradient Boosting, Clustering, and DBSCAN. Python numerical and Scientific Libraries Numpy and Scipy have also been designed

Project Address:

https://link.zhihu.com/?target=http%3A//www.github.com/scikit-learn/scikit-learn

A high efficiency Ramp

Why you should check it out: Ramp is a library for developing solutions to speed prototyping in machine learning in Python. Ramp is a lightweight pluggable framework for pandas based machine learning. Its existing Python machine learning and statistics tools (sciKit-learn, RPY2, etc.), Ramp, provide a simple declarative syntax exploration to implement algorithms and transformations quickly and efficiently.

The project address

http://www.github.com/kvh/ramp

Three,STYLE2PAINTS: Powerful AI for paints

Recommended reason: The new generation of powerful line draft color AI, can be uploaded according to the user’s custom color line draft color. The project provides online access to the site, which is very easy to use.

[image upload failed…(image-a09DB7-1513783284687)]

The project address

https://www.oschina.net/p/style2paints

Four,SerpentAI: A Python based learning framework for teaching AI to play games

Why you should check it out: SerpentAI aims to provide a valuable tool for machine learning and AI research. But at the same time, it is also very interesting for lovers.

[image upload failed…(image-d786a5-1513783284687)]

Serpent.ai contains a number of support modules that provide solutions to scenarios that are often encountered when using games as a development environment, as well as CLI tools to accelerate development. Supports Linux, Windows, and MacOS.

SerpentAI is a Game Agent framework (ps: machine players are often called Agents in order to distinguish between players in man-machine battles) that is simple and powerful. It can turn any Game into a Sandbox environment written in Python in which developers can experiment with the Game Agent, using Python code that developers are very familiar with.

The project address

https://www.oschina.net/p/serpentai

Five,Synaptic. Js: Neural network library for browsers

Why you should check it out: Synaptic. Js is a JavaScript neural network library for Node.js and browsers that can build and train basically any type of first or even second order neural network.

Four classical neural network algorithms are built into the project: Multilayer perceptrons, Multilayer long-short Term memory networks, Liquid State machines Machine), Hopfield neural network. With Synaptic. Js, you can easily test and compare the performance of different architectures.

The project address

https://www.oschina.net/p/serpentai

Vi.Snake-AI: Artificial intelligence for Snake games

Why you should check it out: An AI for snake game written in C/C++. Using shortest path, longest path, artificial intelligence algorithm.

The AI’s goal is to get the snake to eat as much food as possible until the entire map is full.

Demo

[image-3b3C76-1513783284687] [image-3b3C76-1513783284687]

The project address

https://www.oschina.net/p/snake-ai

Seven,Uncaptcha: AI algorithm for cracking reCAPTCHA systems

Why we recommend it: unCAPTCHA beats the Google reCAPTCHA system 85% of the time. It relies on audio captcha attacks – using browser automation software to parse the necessary elements and recognize speech numbers, and deliver those numbers programmatically, ultimately successfully tricking the target website.

[image upload failed…(image-c9e0C3-1513783284687)]

The project address

https://www.oschina.net/p/uncaptcha

Eight,Sockeye: Neural machine translation framework based on Apache MXNet

Why you should check it out: Sockeye is a fast and extensible deep learning library based on Apache MXNet.

The Sockeye codebase has a unique advantage from MXNet. For example, Sockeye combines declarative and imperative programming styles through symbolic and imperative MXNet apis; It can also train models on multiple Gpus in parallel.

Sockeye implements the current best sequence-to-sequence model on MXNet. It also provides appropriate defaults for all sequence-to-sequence model hyperparameters. For optimization, there is no need to worry about stopping criteria, metric tracking, or weight initialization. You can simply run the provided training command line interface (CLI) and easily change the underlying model architecture.

The project address

https://www.oschina.net/p/sockeye

Eight,CycleGAN: Generates adversarial network image processing tools

Why you should check it out: It’s a powerful tool that not only “restores” a painting to a photo (sort of a “backfilter”), but also turns summer into winter or a regular horse into a zebra.

[Image upload failed…(image-83e636-1513783284687)]

Unlike other AI paintings, CycleGAN’s team tried to build a two-way algorithm that could be converted in both directions without losing information. In CycleGAN, the details of the photos are required to be completely preserved, and the researchers hope to be able to input an image into CycleGAN and transform it many times (photo → painting → photo → painting → photo), and eventually get the same or similar image as the original one.

[image upload failed…(image-46159D-1513783284687)]

The project address

https://www.oschina.net/p/cyclegan

Ten,Deeplearn.js: hardware-accelerated machine learning JavaScript library

Deeplearn.js is an open source JavaScript library from Google that can be used for machine intelligence and accelerate WebGL. Deeplearn.js runs completely in the browser, requires no installation, and requires no back-end processing.

[Image upload failed…(image-89D857-1513783284687)]

Deeplearn.js provides efficient machine learning building blocks that allow us to train neural networks in a browser or run pre-trained models in inferential mode. It provides an API for building a differentiable data flow graph, as well as a series of straightforward mathematical functions.

While machine learning libraries on browsers have existed for years (e.g. Andrej Karpathy’s ConvnetJS), they are limited by JavaScript speed or are limited to reasoning and cannot be used for training (e.g. TensorFire). In contrast, deeplearn.js achieves significant acceleration by taking advantage of WebGL’s ability to perform computations on gpus and perform full backpropagation.

The project address

https://www.oschina.net/p/deeplearn-js

Eleven,TensorFire: A webGL-based browser-side neural network framework

Why you should check it out: TensorFire is a WebGL-based neural network framework that runs in a browser. Applications written using TensorFire can implement cutting-edge deep learning algorithms while running directly in modern browsers without any installation or configuration.

[image-2951b5-1513783284687] [image-2951b5-1513783284687]

TensorFire is nearly a hundredfold faster than previous neural network frameworks in some browsers, even matching the performance of code running on native cpus.

Developers can also use the underlying interfaces provided by TensorFire for other high-performance computing, such as PageRank, cellular automata simulation, image conversion and filtering, and more.

The project address

https://www.oschina.net/p/tensorfire

Twelve,Php-ml: PHP machine learning library

We all know that Python or C++ offer more machine learning libraries, but most of them are complex enough to make configuration a pain for beginners. Php-ml machine learning library although there is no particularly sophisticated algorithms, but it has the most basic machine learning, classification and other algorithms, small projects or small companies to do some simple data analysis, prediction and so on enough.

[image upload failed…(image-9a5C74-1513783284687)]

Php-ml is a machine learning library written in PHP. It also includes algorithm, cross validation, neural network, preprocessing, feature extraction and so on.

The project address

https://www.oschina.net/p/php-ml

To read more

Android advanced FFmpeg video playback

11 great Android open Source projects

11 Open Source Projects Android Developers can’t Miss

NDK project actual combat – high imitation 360 mobile phone assistant uninstall monitoring

About artificial intelligence projects, I believe that we have seen or used a lot, but most of them look very “high”, let a person feel to master them like learning the dragon slaying skills. In fact, there are many ai projects that are useful and interesting to use. Here are 12 open source AI projects with unique features.

Scikit-learn for Multiple clustering

A Python module for machine learning based on Scipy features a variety of classification, regression, and clustering algorithms including support vector machines, logistic regression, Naive Bayes Classifier, Random forest, Gradient Boosting, Clustering, and DBSCAN. Python numerical and Scientific Libraries Numpy and Scipy have also been designed

Project Address:

https://link.zhihu.com/?target=http%3A//www.github.com/scikit-learn/scikit-learn

A high efficiency Ramp

Why you should check it out: Ramp is a library for developing solutions to speed prototyping in machine learning in Python. Ramp is a lightweight pluggable framework for pandas based machine learning. Its existing Python machine learning and statistics tools (sciKit-learn, RPY2, etc.), Ramp, provide a simple declarative syntax exploration to implement algorithms and transformations quickly and efficiently.

The project address

http://www.github.com/kvh/ramp

Three,STYLE2PAINTS: Powerful AI for paints

Recommended reason: The new generation of powerful line draft color AI, can be uploaded according to the user’s custom color line draft color. The project provides online access to the site, which is very easy to use.

[image upload failed…(image-a09DB7-1513783284687)]

The project address

https://www.oschina.net/p/style2paints

Four,SerpentAI: A Python based learning framework for teaching AI to play games

Why you should check it out: SerpentAI aims to provide a valuable tool for machine learning and AI research. But at the same time, it is also very interesting for lovers.

[image upload failed…(image-d786a5-1513783284687)]

Serpent.ai contains a number of support modules that provide solutions to scenarios that are often encountered when using games as a development environment, as well as CLI tools to accelerate development. Supports Linux, Windows, and MacOS.

SerpentAI is a Game Agent framework (ps: machine players are often called Agents in order to distinguish between players in man-machine battles) that is simple and powerful. It can turn any Game into a Sandbox environment written in Python in which developers can experiment with the Game Agent, using Python code that developers are very familiar with.

The project address

https://www.oschina.net/p/serpentai

Five,Synaptic. Js: Neural network library for browsers

Why you should check it out: Synaptic. Js is a JavaScript neural network library for Node.js and browsers that can build and train basically any type of first or even second order neural network.

Four classical neural network algorithms are built into the project: Multilayer perceptrons, Multilayer long-short Term memory networks, Liquid State machines Machine), Hopfield neural network. With Synaptic. Js, you can easily test and compare the performance of different architectures.

The project address

https://www.oschina.net/p/serpentai

Vi.Snake-AI: Artificial intelligence for Snake games

Why you should check it out: An AI for snake game written in C/C++. Using shortest path, longest path, artificial intelligence algorithm.

The AI’s goal is to get the snake to eat as much food as possible until the entire map is full.

Demo

[image upload failed…(image-3b3C76-1513783284687)]

The project address

https://www.oschina.net/p/snake-ai

Seven,Uncaptcha: AI algorithm for cracking reCAPTCHA systems

Why we recommend it: unCAPTCHA beats the Google reCAPTCHA system 85% of the time. It relies on audio captcha attacks – using browser automation software to parse the necessary elements and recognize speech numbers, and deliver those numbers programmatically, ultimately successfully tricking the target website.

[image upload failed…(image-c9e0C3-1513783284687)]

The project address

https://www.oschina.net/p/uncaptcha

Eight,Sockeye: Neural machine translation framework based on Apache MXNet

Why you should check it out: Sockeye is a fast and extensible deep learning library based on Apache MXNet.

The Sockeye codebase has a unique advantage from MXNet. For example, Sockeye combines declarative and imperative programming styles through symbolic and imperative MXNet apis; It can also train models on multiple Gpus in parallel.

Sockeye implements the current best sequence-to-sequence model on MXNet. It also provides appropriate defaults for all sequence-to-sequence model hyperparameters. For optimization, there is no need to worry about stopping criteria, metric tracking, or weight initialization. You can simply run the provided training command line interface (CLI) and easily change the underlying model architecture.

The project address

https://www.oschina.net/p/sockeye

Eight,CycleGAN: Generates adversarial network image processing tools

Why you should check it out: It’s a powerful tool that not only “restores” a painting to a photo (sort of a “backfilter”), but also turns summer into winter or a regular horse into a zebra.

[image-83e636-1513783284687] [Image-83e636-1513783284687]

Unlike other AI paintings, CycleGAN’s team tried to build a two-way algorithm that could be converted in both directions without losing information. In CycleGAN, the details of the photos are required to be completely preserved, and the researchers hope to be able to input an image into CycleGAN and transform it many times (photo → painting → photo → painting → photo), and eventually get the same or similar image as the original one.

[image upload failed…(image-46159D-1513783284687)]

The project address

https://www.oschina.net/p/cyclegan

Ten,Deeplearn.js: hardware-accelerated machine learning JavaScript library

Deeplearn.js is an open source JavaScript library from Google that can be used for machine intelligence and accelerate WebGL. Deeplearn.js runs completely in the browser, requires no installation, and requires no back-end processing.

[Image upload failed…(image-89D857-1513783284687)]

Deeplearn.js provides efficient machine learning building blocks that allow us to train neural networks in a browser or run pre-trained models in inferential mode. It provides an API for building a differentiable data flow graph, as well as a series of straightforward mathematical functions.

While machine learning libraries on browsers have existed for years (e.g. Andrej Karpathy’s ConvnetJS), they are limited by JavaScript speed or are limited to reasoning and cannot be used for training (e.g. TensorFire). In contrast, deeplearn.js achieves significant acceleration by taking advantage of WebGL’s ability to perform computations on gpus and perform full backpropagation.

Project address about artificial intelligence projects, I believe we have seen or used a lot, but most of them look very “lofty”, let a person feel to master them like learning to slay the dragon. In fact, there are many ai projects that are useful and interesting to use. Here are 12 open source AI projects with unique features.

Scikit-learn for Multiple clustering

A Python module for machine learning based on Scipy features a variety of classification, regression, and clustering algorithms including support vector machines, logistic regression, Naive Bayes Classifier, Random forest, Gradient Boosting, Clustering, and DBSCAN. Python numerical and Scientific Libraries Numpy and Scipy have also been designed

Project Address:

https://link.zhihu.com/?target=http%3A//www.github.com/scikit-learn/scikit-learn

A high efficiency Ramp

Why you should check it out: Ramp is a library for developing solutions to speed prototyping in machine learning in Python. Ramp is a lightweight pluggable framework for pandas based machine learning. Its existing Python machine learning and statistics tools (sciKit-learn, RPY2, etc.), Ramp, provide a simple declarative syntax exploration to implement algorithms and transformations quickly and efficiently.

The project address

http://www.github.com/kvh/ramp

Three,STYLE2PAINTS: Powerful AI for paints

Recommended reason: The new generation of powerful line draft color AI, can be uploaded according to the user’s custom color line draft color. The project provides online access to the site, which is very easy to use.

[image failed to upload…(image-cf04d1-1513783312474)]

The project address

https://www.oschina.net/p/style2paints

Four,SerpentAI: A Python based learning framework for teaching AI to play games

Why you should check it out: SerpentAI aims to provide a valuable tool for machine learning and AI research. But at the same time, it is also very interesting for lovers.

[image upload failed…(image-1b6d7C-1513783312474)]

Serpent.ai contains a number of support modules that provide solutions to scenarios that are often encountered when using games as a development environment, as well as CLI tools to accelerate development. Supports Linux, Windows, and MacOS.

SerpentAI is a Game Agent framework (ps: machine players are often called Agents in order to distinguish between players in man-machine battles) that is simple and powerful. It can turn any Game into a Sandbox environment written in Python in which developers can experiment with the Game Agent, using Python code that developers are very familiar with.

The project address

https://www.oschina.net/p/serpentai

Five,Synaptic. Js: Neural network library for browsers

Why you should check it out: Synaptic. Js is a JavaScript neural network library for Node.js and browsers that can build and train basically any type of first or even second order neural network.

Four classical neural network algorithms are built into the project: Multilayer perceptrons, Multilayer long-short Term memory networks, Liquid State machines Machine), Hopfield neural network. With Synaptic. Js, you can easily test and compare the performance of different architectures.

The project address

https://www.oschina.net/p/serpentai

Vi.Snake-AI: Artificial intelligence for Snake games

Why you should check it out: An AI for snake game written in C/C++. Using shortest path, longest path, artificial intelligence algorithm.

The AI’s goal is to get the snake to eat as much food as possible until the entire map is full.

Demo

[image upload failed…(image-dfc3C6-1513783312474)]

The project address

https://www.oschina.net/p/snake-ai

Seven,Uncaptcha: AI algorithm for cracking reCAPTCHA systems

Why we recommend it: unCAPTCHA beats the Google reCAPTCHA system 85% of the time. It relies on audio captcha attacks – using browser automation software to parse the necessary elements and recognize speech numbers, and deliver those numbers programmatically, ultimately successfully tricking the target website.

[Image upload failed…(image-24AFB-1513783312474)]

The project address

https://www.oschina.net/p/uncaptcha

Eight,Sockeye: Neural machine translation framework based on Apache MXNet

Why you should check it out: Sockeye is a fast and extensible deep learning library based on Apache MXNet.

The Sockeye codebase has a unique advantage from MXNet. For example, Sockeye combines declarative and imperative programming styles through symbolic and imperative MXNet apis; It can also train models on multiple Gpus in parallel.

Sockeye implements the current best sequence-to-sequence model on MXNet. It also provides appropriate defaults for all sequence-to-sequence model hyperparameters. For optimization, there is no need to worry about stopping criteria, metric tracking, or weight initialization. You can simply run the provided training command line interface (CLI) and easily change the underlying model architecture.

The project address

https://www.oschina.net/p/sockeye

Eight,CycleGAN: Generates adversarial network image processing tools

Why you should check it out: It’s a powerful tool that not only “restores” a painting to a photo (sort of a “backfilter”), but also turns summer into winter or a regular horse into a zebra.

[image upload failed…(image-b795C3-1513783312474)]

Unlike other AI paintings, CycleGAN’s team tried to build a two-way algorithm that could be converted in both directions without losing information. In CycleGAN, the details of the photos are required to be completely preserved, and the researchers hope to be able to input an image into CycleGAN and transform it many times (photo → painting → photo → painting → photo), and eventually get the same or similar image as the original one.

[image upload failed…(image-bd1C1C-1513783312474)]

The project address

https://www.oschina.net/p/cyclegan

Ten,Deeplearn.js: hardware-accelerated machine learning JavaScript library

Deeplearn.js is an open source JavaScript library from Google that can be used for machine intelligence and accelerate WebGL. Deeplearn.js runs completely in the browser, requires no installation, and requires no back-end processing.

[image uploading failed…(image-d198e0-1513783312474)]

Deeplearn.js provides efficient machine learning building blocks that allow us to train neural networks in a browser or run pre-trained models in inferential mode. It provides an API for building a differentiable data flow graph, as well as a series of straightforward mathematical functions.

While machine learning libraries on browsers have existed for years (e.g. Andrej Karpathy’s ConvnetJS), they are limited by JavaScript speed or are limited to reasoning and cannot be used for training (e.g. TensorFire). In contrast, deeplearn.js achieves significant acceleration by taking advantage of WebGL’s ability to perform computations on gpus and perform full backpropagation.

The project address

https://www.oschina.net/p/deeplearn-js

Eleven,TensorFire: A webGL-based browser-side neural network framework

Why you should check it out: TensorFire is a WebGL-based neural network framework that runs in a browser. Applications written using TensorFire can implement cutting-edge deep learning algorithms while running directly in modern browsers without any installation or configuration.

[image upload failed…(image-7918D5-1513783312474)]

TensorFire is nearly a hundredfold faster than previous neural network frameworks in some browsers, even matching the performance of code running on native cpus.

Developers can also use the underlying interfaces provided by TensorFire for other high-performance computing, such as PageRank, cellular automata simulation, image conversion and filtering, and more.

The project address

https://www.oschina.net/p/tensorfire

Twelve,Php-ml: PHP machine learning library

We all know that Python or C++ offer more machine learning libraries, but most of them are complex enough to make configuration a pain for beginners. Php-ml machine learning library although there is no particularly sophisticated algorithms, but it has the most basic machine learning, classification and other algorithms, small projects or small companies to do some simple data analysis, prediction and so on enough.

[image upload failed…(image-2be3BD-1513783312474)]

Php-ml is a machine learning library written in PHP. It also includes algorithm, cross validation, neural network, preprocessing, feature extraction and so on.

The project address

https://www.oschina.net/p/php-ml

To read more

Android advanced FFmpeg video playback

11 great Android open Source projects

11 Open Source Projects Android Developers can’t Miss

NDK project actual combat – high imitation 360 mobile phone assistant uninstall monitoring

Believe in yourself, nothing can not be done, only unexpected, if you feel this article is helpful to you, welcome to pay attention to. codeGoogler

https://www.oschina.net/p/deeplearn-js

Eleven,TensorFire: A webGL-based browser-side neural network framework

Why you should check it out: TensorFire is a WebGL-based neural network framework that runs in a browser. Applications written using TensorFire can implement cutting-edge deep learning algorithms while running directly in modern browsers without any installation or configuration.

[image-2951b5-1513783284687] [image-2951b5-1513783284687]

TensorFire is nearly a hundredfold faster than previous neural network frameworks in some browsers, even matching the performance of code running on native cpus.

Developers can also use the underlying interfaces provided by TensorFire for other high-performance computing, such as PageRank, cellular automata simulation, image conversion and filtering, and more.

The project address

https://www.oschina.net/p/tensorfire

Twelve,Php-ml: PHP machine learning library

We all know that Python or C++ offer more machine learning libraries, but most of them are complex enough to make configuration a pain for beginners. Php-ml machine learning library although there is no particularly sophisticated algorithms, but it has the most basic machine learning, classification and other algorithms, small projects or small companies to do some simple data analysis, prediction and so on enough.

[image upload failed…(image-9a5C74-1513783284687)]

Php-ml is a machine learning library written in PHP. It also includes algorithm, cross validation, neural network, preprocessing, feature extraction and so on.

The project address

https://www.oschina.net/p/php-ml

To read more

Android advanced FFmpeg video playback

11 great Android open Source projects

11 Open Source Projects Android Developers can’t Miss

NDK project actual combat – high imitation 360 mobile phone assistant uninstall monitoring

About artificial intelligence projects, I believe that we have seen or used a lot, but most of them look very “high”, let a person feel to master them like learning the dragon slaying skills. In fact, there are many ai projects that are useful and interesting to use. Here are 12 open source AI projects with unique features.

Scikit-learn for Multiple clustering

A Python module for machine learning based on Scipy features a variety of classification, regression, and clustering algorithms including support vector machines, logistic regression, Naive Bayes Classifier, Random forest, Gradient Boosting, Clustering, and DBSCAN. Python numerical and Scientific Libraries Numpy and Scipy have also been designed

Project Address:

https://link.zhihu.com/?target=http%3A//www.github.com/scikit-learn/scikit-learn

A high efficiency Ramp

Why you should check it out: Ramp is a library for developing solutions to speed prototyping in machine learning in Python. Ramp is a lightweight pluggable framework for pandas based machine learning. Its existing Python machine learning and statistics tools (sciKit-learn, RPY2, etc.), Ramp, provide a simple declarative syntax exploration to implement algorithms and transformations quickly and efficiently.

The project address

http://www.github.com/kvh/ramp

Three,STYLE2PAINTS: Powerful AI for paints

Recommended reason: The new generation of powerful line draft color AI, can be uploaded according to the user’s custom color line draft color. The project provides online access to the site, which is very easy to use.

[image upload failed…(image-a09DB7-1513783284687)]

The project address

https://www.oschina.net/p/style2paints

Four,SerpentAI: A Python based learning framework for teaching AI to play games

Why you should check it out: SerpentAI aims to provide a valuable tool for machine learning and AI research. But at the same time, it is also very interesting for lovers.

[image upload failed…(image-d786a5-1513783284687)]

Serpent.ai contains a number of support modules that provide solutions to scenarios that are often encountered when using games as a development environment, as well as CLI tools to accelerate development. Supports Linux, Windows, and MacOS.

SerpentAI is a Game Agent framework (ps: machine players are often called Agents in order to distinguish between players in man-machine battles) that is simple and powerful. It can turn any Game into a Sandbox environment written in Python in which developers can experiment with the Game Agent, using Python code that developers are very familiar with.

The project address

https://www.oschina.net/p/serpentai

Five,Synaptic. Js: Neural network library for browsers

Why you should check it out: Synaptic. Js is a JavaScript neural network library for Node.js and browsers that can build and train basically any type of first or even second order neural network.

Four classical neural network algorithms are built into the project: Multilayer perceptrons, Multilayer long-short Term memory networks, Liquid State machines Machine), Hopfield neural network. With Synaptic. Js, you can easily test and compare the performance of different architectures.

The project address

https://www.oschina.net/p/serpentai

Vi.Snake-AI: Artificial intelligence for Snake games

Why you should check it out: An AI for snake game written in C/C++. Using shortest path, longest path, artificial intelligence algorithm.

The AI’s goal is to get the snake to eat as much food as possible until the entire map is full.

Demo

[image-3b3C76-1513783284687] [image-3b3C76-1513783284687]

The project address

https://www.oschina.net/p/snake-ai

Seven,Uncaptcha: AI algorithm for cracking reCAPTCHA systems

Why we recommend it: unCAPTCHA beats the Google reCAPTCHA system 85% of the time. It relies on audio captcha attacks – using browser automation software to parse the necessary elements and recognize speech numbers, and deliver those numbers programmatically, ultimately successfully tricking the target website.

[image upload failed…(image-c9e0C3-1513783284687)]

The project address

https://www.oschina.net/p/uncaptcha

Eight,Sockeye: Neural machine translation framework based on Apache MXNet

Why you should check it out: Sockeye is a fast and extensible deep learning library based on Apache MXNet.

The Sockeye codebase has a unique advantage from MXNet. For example, Sockeye combines declarative and imperative programming styles through symbolic and imperative MXNet apis; It can also train models on multiple Gpus in parallel.

Sockeye implements the current best sequence-to-sequence model on MXNet. It also provides appropriate defaults for all sequence-to-sequence model hyperparameters. For optimization, there is no need to worry about stopping criteria, metric tracking, or weight initialization. You can simply run the provided training command line interface (CLI) and easily change the underlying model architecture.

The project address

https://www.oschina.net/p/sockeye

Eight,CycleGAN: Generates adversarial network image processing tools

Why you should check it out: It’s a powerful tool that not only “restores” a painting to a photo (sort of a “backfilter”), but also turns summer into winter or a regular horse into a zebra.

[image-83e636-1513783284687] [Image-83e636-1513783284687]

Unlike other AI paintings, CycleGAN’s team tried to build a two-way algorithm that could be converted in both directions without losing information. In CycleGAN, the details of the photos are required to be completely preserved, and the researchers hope to be able to input an image into CycleGAN and transform it many times (photo → painting → photo → painting → photo), and eventually get the same or similar image as the original one.

[image upload failed…(image-46159D-1513783284687)]

The project address

https://www.oschina.net/p/cyclegan

Ten,Deeplearn.js: hardware-accelerated machine learning JavaScript library

Deeplearn.js is an open source JavaScript library from Google that can be used for machine intelligence and accelerate WebGL. Deeplearn.js runs completely in the browser, requires no installation, and requires no back-end processing.

[Image upload failed…(image-89D857-1513783284687)]

Deeplearn.js provides efficient machine learning building blocks that allow us to train neural networks in a browser or run pre-trained models in inferential mode. It provides an API for building a differentiable data flow graph, as well as a series of straightforward mathematical functions.

While machine learning libraries on browsers have existed for years (e.g. Andrej Karpathy’s ConvnetJS), they are limited by JavaScript speed or are limited to reasoning and cannot be used for training (e.g. TensorFire). In contrast, deeplearn.js achieves significant acceleration by taking advantage of WebGL’s ability to perform computations on gpus and perform full backpropagation.

The project address

https://www.oschina.net/p/deeplearn-js

Eleven,TensorFire: A webGL-based browser-side neural network framework

Why you should check it out: TensorFire is a WebGL-based neural network framework that runs in a browser. Applications written using TensorFire can implement cutting-edge deep learning algorithms while running directly in modern browsers without any installation or configuration.

[image upload failed…(image-2951b5-1513783284687)]

TensorFire is nearly a hundredfold faster than previous neural network frameworks in some browsers, even matching the performance of code running on native cpus.

Developers can also use the underlying interfaces provided by TensorFire for other high-performance computing, such as PageRank, cellular automata simulation, image conversion and filtering, and more.

The project address

https://www.oschina.net/p/tensorfire

Twelve,Php-ml: PHP machine learning library

We all know that Python or C++ offer more machine learning libraries, but most of them are complex enough to make configuration a pain for beginners. Php-ml machine learning library although there is no particularly sophisticated algorithms, but it has the most basic machine learning, classification and other algorithms, small projects or small companies to do some simple data analysis, prediction and so on enough.

Php-ml is a machine learning library written in PHP. It also includes algorithm, cross validation, neural network, preprocessing, feature extraction and so on.

The project address

https://www.oschina.net/p/php-ml

Believe in yourself, there is nothing impossible, only unexpected

If you think this article is helpful to you, welcome to follow the wechat public number: Terminal R&D Department