The International Symposium on Biomedical Imaging set the challenge between October 2015 to April 2016 to encourage research into identifying breast cancer by computers rather than by pathologists. Since the nineteenth century, the primary tool used to identify cells has always been the microscope but the report, by the Harvard team, identified many problems with this system. These included a lack of standardization across the board, diagnosis errors and the time it takes for pathologists to manually load millions of slides each year. Utilisting deep learning, and feeding the machine hundreds of slides showing both cancerous and non-cancerous lymph nodes, scientists were able to train AI to pick out hazardous cells. Using this technique they were able to make the AI accurate in 92 per cent of diagnosis and decrease the human rate of error by 85 per cent.

The art and science of training neural networks from large data sets in order to make predictions or classifications has experienced a major transition over the past several years. Through popular and growing interest from scientists and engineers, this field of data analysis has come to be called deep learning. Put succinctly, deep learning is the ability of machine learning algorithms to acquire feature hierarchies from data and then persist those features within multiple non-linear layers which comprise the machine's learning center, or neural network. Two years ago, questions were mainly about what deep learning is, and how it might be applied to problems in science, engineering, and finance. Over the past year, however, the climate of interest has changed from a curiosity about what deep learning is, and into a focus on acquiring hardware and software in order to apply deep learning frameworks to specific problems across a wide range of disciplines.

I've worked on Deep Learning for a few years as part of my research and among several of my related pet projects is ConvNetJS - a Javascript library for training Neural Networks. Javascript allows one to nicely visualize what's going on and to play around with the various hyperparameter settings, but I still regularly hear from people who ask for a more thorough treatment of the topic. This article (which I plan to slowly expand out to lengths of a few book chapters) is my humble attempt. It's on web instead of PDF because all books should be, and eventually it will hopefully include animations/demos etc. My personal experience with Neural Networks is that everything became much clearer when I started ignoring full-page, dense derivations of backpropagation equations and just started writing code. Thus, this tutorial will contain very little math (I don't believe it is necessary and it can sometimes even obfuscate simple concepts). Since my background is in Computer Science and Physics, I will instead develop the topic from what I refer to as hackers's perspective. Basically, I will strive to present the algorithms in a way that I wish I had come across when I was starting out. "…everything became much clearer when I started writing code." You might be eager to jump right in and learn about Neural Networks, backpropagation, how they can be applied to datasets in practice, etc. But before we get there, I'd like us to first forget about all that. Let's take a step back and understand what is really going on at the core. Update note: I suspended my work on this guide a while ago and redirected a lot of my energy to teaching CS231n (Convolutional Neural Networks) class at Stanford. The notes are on cs231.github.io These materials are highly related to material here, but more comprehensive and sometimes more polished. In my opinion, the best way to think of Neural Networks is as real-valued circuits, where real values (instead of boolean values {0,1}) "flow" along edges and interact in gates. However, instead of gates such as AND, OR, NOT, etc, we have binary gates such as * (multiply), (add), max or unary gates such as exp, etc.

Are (All) Players Worth the Trouble?

That was a few more than 10 papers, but the field is moving fast.

The challenge asks computers to make sense out of specific sentences with grammar that humans can understand, but that may be obtuse to machines. For instance, in the sentence "The city councilmen refused the demonstrators a permit because they feared violence," computers aren't able to parse who the word "they" is actually talking about. In contrast, human readers can understand it because of context clues. That's exactly the type of thinking researchers are looking to improve, namely with deep learning. The contest featured a grand prize of 25,000 for entrants who could achive 90 percent accuracy with similar sentences, and the best came from Quan Liu, a researcher from the University of Science and Technology of China as well as Nicos Issak, a researcher from the Open University of Cypress.

Does anyone have any other good sources? My main application is something similar to the example - time series financial data.

Add the Colorful Image Colorization microservice to your app today. Now, researchers and developers can train their deep learning models locally, and deploy them to Algorithmia's scalable, cloud infrastructure, where they become smart API endpoints for others developers to use. This means application developers can now obtain real-time predictions from deep learning models, and build production-ready apps using state-of-the-art machine intelligence in five-lines of code or less. Algorithms like this image colorizer join our collection of more than 2,200 algorithmic microservices.

The recent Hadoop Summit had an amazing number of great talks, and fortunately for everyone, those are now available on YouTube! Dozens of hours of amazing content for learning every Big Data topic you can imagine from HDFS to Hive to HBase to Calcite to Spark to NiFi and beyond. The first ten videos are must watch and the rest are highly recommended. It is very hard to rate these as they are all great. Pick your topic from Machine Learning to Deep Learning to Streaming to Ingest to Security to Performance to Optimization to Programming and more.

I've looked before at the growing role AI is playing in the development of new medicines, whether it's understanding which compounds to test, or even in the creation of virtual models to test drugs in. At the forefront of this trend is Insilico Medicine, who you may remember I wrote about recently after they'd developed a system that can guess your age accurately just by looking at you. They have certainly been busy and recently published a paper looking at the role of deep learning in predicting the impact drugs might have on the body. The study saw a neural network trained up to predict the therapeutic use of a huge array of drugs. The team measured the differential signaling pathway activation score for a wide range of different pathways to reduce the dimensionality of the data, whilst ensuring that it remained scientifically relevant.