This is a collection of free resources beyond the regularly shared books, MOOCs, and courses, mostly from over the past year. They start from zero and progress accordingly, and are suitable for individuals looking to pick up some of the basic ideas, before hopefully branching out further (see the final 2 resources listed below for more on that). These resources are not presented in any particular order, so feel free to pursue those which look most enticing to you. All credit goes the the individual authors of the respective materials, without whose hard work we would not have the benefit of learning from such great content. For many good reasons, much of the highest quality machine learning educational resources tend to have a very strong focus on theory, especially at the beginning.

WHEN TAY MADE HER DEBUT in March 2016, Microsoft had high hopes for the artificial intelligence–powered "social chatbot." Like the automated, text-based chat programs that many people had already encountered on e-commerce sites and in customer service conversations, Tay could answer written questions; by doing so on Twitter and other social media, she could engage with the masses. But rather than simply doling out facts, Tay was engineered to converse in a more sophisticated way--one that had an emotional dimension. She would be able to show a sense of humor, to banter with people like a friend. Her creators had even engineered her to talk like a wisecracking teenage girl. When Twitter users asked Tay who her parents were, she might respond, "Oh a team of scientists in a Microsoft lab. They're what u would call my parents." If someone asked her how her day had been, she could quip, "omg totes exhausted."

The robot arm is performing a peculiar kind of Sisyphean task. It hovers over a glistening pile of cooked chicken parts, dips down, and retrieves a single piece. A moment later, it swings around and places the chunk of chicken, ever so gently, into a bento box moving along a conveyor belt. This robot, created by a San Francisco–based company called Osaro, is smarter than any you've seen before. The software that controls it has taught it to pick and place chicken in about five seconds--faster than your average food-processing worker.

This August, some of the world's best professional gamers will travel to Vancouver to fight for millions of dollars in the world's most valuable esports competition. They'll be joined by a team of five artificial intelligence bots backed by Elon Musk, trying to set a new marker for the power of machine learning. The bots were developed by OpenAI, an independent research institute the Tesla CEO cofounded in 2015 to advance AI and prevent the technology from turning dangerous. Vancouver is hosting the annual world championship of Dota 2, one of the internet's most-watched videogames. The prize purse is more than $15 million and growing, exceeding the $11 million at stake at golf's Masters.

Early applications of deep learning to imagery and video focused primarily on cataloging that content, identifying the objects, activities, locations and text within. As neural algorithms have improved and new techniques developed, there has been an increasing focus on using deep learning approaches to actually generate completely new visual content autonomously. The cost of such AI generated synthetic content is dropping rapidly to the point that in the very near future you'll likely be able to generate it on your smartphone with a click of a button. These images and videos are a far cry from the ham-handed Photoshop jobs of yesteryear, with some appearing nearly flawless even to a trained eye. At the same time, we've taught society that "seeing is believing" and to put far more trust in the visual material we see online – an image might be miscaptioned, but the picture itself is likely real.

Since Alan Turing first posed the question "can machines think?" in his seminal paper in 1950, "Computing Machinery and Intelligence", Artificial Intelligence (AI) has failed to deliver on its promise. That is, Artificial General Intelligence. There have, however, been incredible advances in the field, including Deep Blue beating the world's best chess player, the birth of autonomous vehicles, and Google's DeepMind beating the world's best AlphaGo player. The current achievements represent the culmination of research and development that occurred over more than 65 years. Importantly, during this period there were two well documented AI Winters that almost completely debunked the promise of AI.

When humans and artificial intelligence face off in a game, like chess or Go, it's typically a one-against-one affair. Each player, human or AI, just has to outsmart a single opponent on a board that only changes when the players make a move. OpenAI is announcing today (June 25) that its newest AI bots can hold their own as a team of five against human gamers at Dota 2, a multiplayer game popular in e-sports for its complexity and necessity for teamwork. The AI research lab is looking to take the bots to Dota 2 championship matches in August to compete against the pros. Dota 2 is a challenging game for AI to master simply because of the amount of decisions that the players have to juggle. While chess can end in fewer than 40 moves, and Go fewer than 150, OpenAI's Dota 2 bots make 20,000 moves over the course of a 45 minute game.

This article comes from Deep Learning Patterns. Note to reader: Diving into this material here can be a bit overwhelming. One way though to get an understanding of the thought process is to follow the Intuition Machine blog. Deep Learning Architecture can be described as a new method or style of building machine learning systems. Deep Learning is more than likely to lead to more advanced forms of artificial intelligence.

This new core has been specifically designed to enhance the performance of deep learning by 10X and enable more neural network processing per square millimeter. Many companies are using FPGA to implement AI and more specifically machine learning, deep learning and neural networks as approaches to achieve AI. The key function needed for AI are matrix multipliers, which consist of arrays of MACs (multiplier accumulators). In existing FPGA and eFPGAs, the MACs are optimized for DSPs with larger multipliers, pre-adders and other logic which are overkill for AI. For AI applications, smaller multipliers such as 16 bits or 8 bits, with the ability to support both modes with accumulators, allow more neural network processing per square millimeter.

There are certainly a lot of guides to assist you build great deep learning (DL) setups on Linux or Mac OS (including with Tensorflow which, unfortunately, as of this posting, cannot be easily installed on Windows), but few care about building an efficient Windows 10-native setup. Most focus on running an Ubuntu VM hosted on Windows or using Docker, unnecessary - and ultimately sub-optimal - steps. We also found enough misguiding/deprecated information out there to make it worthwhile putting together a step-by-step guide for the latest stable versions of Keras, Tensorflow, CNTK, MXNet, and PyTorch. Used either together (e.g., Keras with Tensorflow backend), or independently -- PyTorch cannot be used as a Keras backend, TensorFlow can be used on its own -- they make for some of the most powerful deep learning python libraries to work natively on Windows. If you must run your DL setup on Windows 10, then the information contained here will hopefully be useful to you.