Deep Learning Research Review Week 2: Reinforcement Learning
This is the 2nd installment of a new series called Deep Learning Research Review. Every couple weeks or so, I’ll be summarizing and explaining research papers in specific subfields of deep learning. This week focuses on Reinforcement Learning. Last time was Generative Adversarial Networks ICYMI Introduction to Reinforcement Learning... Read more
Artificial Neural Networks (ANN) Introduction
Training a Computer to Recognize your Handwriting Take a look at the picture below above and try to identify what it is. One should be able to tell that it is a giraffe, despite it being strangely fat. We recognize images and objects instantly, even if these images are... Read more
Can neural networks solve any problem?
Visualizing the Universal Approximation Theorem At some point in your deep learning journey you probably came across the Universal Approximation Theorem. A feedforward network with a single layer is sufficient to represent any function, but the layer may be infeasibly large and may fail to learn and generalize correctly.... Read more
Learning in Brains and Machines (1): Temporal Differences
We all make mistakes, and as is often said, only then can we learn. Our mistakes allow us to gain insight, and the ability to make better judgements and fewer mistakes in future. In their influential paper, the neuroscientists Robert Rescorla and Allan Wagner put this more succinctly, ‘organisms only learn when... Read more
Deep Learning Research Review Week 1: Generative Adversarial Nets
This week, I’ll be doing a new series called Deep Learning Research Review. Every couple weeks or so, I’ll be summarizing and explaining research papers in specific subfields of deep learning. This week I’ll begin with Generative Adversarial Networks.  Introduction According to Yann LeCun, “adversarial training is the coolest... Read more
In part two of my XKCD font saga I was able to separate strokes from the XKCD handwriting dataset into many smaller images. I also handled the easier cases of merging some of the strokes back together – I particularly focussed on “dotty” or “liney” type glyphs, such as... Read more
An Introduction to Deep Learning using nolearn
NOTE: If you are having trouble with nolearn working properly, make sure you are using version 0.5b1 available here. Otherwise you may run into problems. One of the most well known problems in machine learning regards how to categorize handwritten numbers automatically. Basically, the idea is that you have... Read more
Linear algebra cheat sheet for Deep Learning
Beginner’s guide to commonly used operations During Jeremy Howard’s excellent deep learning course I realized I was a little rusty on the prerequisites and my fuzziness was impacting my ability to understand concepts like backpropagation. I decided to put together a few wiki pages on these topics to improve... Read more
A Beginner’s Guide To Understanding Convolutional Neural Networks Part 2
Introduction Link to Part 1 In this post, we’ll go into a lot more of the specifics of ConvNets. Disclaimer: Now, I do realize that some of these topics are quite complex and could be made in whole posts by themselves. In an effort to remain concise yet retain... Read more
Automated analysis of High‐content Microscopy data with Deep Learning
    Deep learning is used to classify protein subcellular localization in genome‐wide microscopy screens of GFP‐tagged yeast strains. The resulting classifier (DeepLoc) outperforms previous classification methods and is transferable across image sets. A deep convolutional neural network (DeepLoc) is trained to classify protein subcellular localization in GFP‐tagged yeast... Read more