background preloader

General Machine learning

Facebook Twitter

Free Machine Learning eBooks - March 2017. By Shai Ben-David and Shai Shalev-Shwartz Machine learning is one of the fastest growing areas of computer science, with far-reaching applications.

Free Machine Learning eBooks - March 2017

The aim of this textbook is to introduce machine learning, and the algorithmic paradigms it offers, in a principled way. OpenNN start. OpenNN start In this tutorial you'll learn how to start using OpenNN: Where can I find information about it?

OpenNN start

Where can I download the library? How can I get support and training? What are the main advantages of using OpenNN? What is the different between OpenNN and Neural Designer? Contents: 1. PCA and ICA Package - File Exchange - MATLAB Central. LibICA - ICA library. FastICA C implementation Martin Tůma Description libICA is an C library that implements the FastICA [1] algorithm for Independent Component Analysis (ICA).

libICA - ICA library

It is based on the CRAN fastICA [2] package for R. Synopsis #include <libICA.h> void fastICA(double** X, int rows, int cols, int compc, double** K, double** W, double** A, double** S); Parametes: pre-processed data matrix [rows, cols] compc number of components to be extracted pre-whitening matrix that projects data onto the first compc principal components estimated un-mixing matrix estimated mixing matrix estimated source matrix Details. Research Blog: Open sourcing the Embedding Projector: a tool for visualizing high dimensional data. Posted by Daniel Smilkov and the Big Picture group Recent advances in Machine Learning (ML) have shown impressive results, with applications ranging from image recognition, language translation, medical diagnosis and more.

Research Blog: Open sourcing the Embedding Projector: a tool for visualizing high dimensional data

With the widespread adoption of ML systems, it is increasingly important for research scientists to be able to explore how the data is being interpreted by the models. However, one of the main challenges in exploring this data is that it often has hundreds or even thousands of dimensions, requiring special tools to investigate the space. To enable a more intuitive exploration process, we are open-sourcing the Embedding Projector, a web application for interactive visualization and analysis of high-dimensional data recently shown as an A.I. Experiment, as part of TensorFlow. We are also releasing a standalone version at, where users can visualize their high-dimensional data without the need to install and run TensorFlow.

An overview of gradient descent optimization algorithms. Note: If you are looking for a review paper, this blog post is also available as an article on arXiv.

An overview of gradient descent optimization algorithms

Table of contents: Gradient descent is one of the most popular algorithms to perform optimization and by far the most common way to optimize neural networks. At the same time, every state-of-the-art Deep Learning library contains implementations of various algorithms to optimize gradient descent (e.g. lasagne's, caffe's, and keras' documentation). These algorithms, however, are often used as black-box optimizers, as practical explanations of their strengths and weaknesses are hard to come by.

This blog post aims at providing you with intuitions towards the behaviour of different algorithms for optimizing gradient descent that will help you put them to use. Gradient descent is a way to minimize an objective function J(θ) parameterized by a model's parameters θ∈Rd by updating the parameters in the opposite direction of the gradient of the objective function ∇θJ(θ) w.r.t. to the parameters. Jupyter Notebook Viewer. 9 Key Deep Learning Papers, Explained. If you are interested in understanding the current state of deep learning, this post outlines and thoroughly summarizes 9 of the most influential contemporary papers in the field.

9 Key Deep Learning Papers, Explained

By Adit Deshpande, UCLA. Introduction In this post, we’ll go into summarizing a lot of the new and important developments in the field of computer vision and convolutional neural networks. We’ll look at some of the most important papers that have been published over the last 5 years and discuss why they’re so important. The first half of the list (AlexNet to ResNet) deals with advancements in general network architecture, while the second half is just a collection of interesting papers in other subareas. 1. The one that started it all (Though some may say that Yann LeCun’s paper in 1998 was the real pioneering publication).

Research Blog: Graph-powered Machine Learning at Google. Posted by Sujith Ravi, Staff Research Scientist, Google Research Recently, there have been significant advances in Machine Learning that enable computer systems to solve complex real-world problems.

Research Blog: Graph-powered Machine Learning at Google

One of those advances is Google’s large scale, graph-based machine learning platform, built by the Expander team in Google Research. A technology that is behind many of the Google products and features you may use everyday, graph-based machine learning is a powerful tool that can be used to power useful features such as reminders in Inbox and smart messaging in Allo, or used in conjunction with deep neural networks to power the latest image recognition system in Google Photos. Learning with Minimal Supervision Much of the recent success in deep learning and machine learning, in general, can be attributed to models that demonstrate high predictive capacity when trained on large amounts of labeled data -- often millions of training examples. .. C++ Library for Audio and Music. SVM - Understanding the math - Part 1 - The margin - SVM Tutorial.