Learn about how creative data processing allows using the full power of deep learning vision for non-vision tasks. — Introduction In recent years, deep learning has revolutionized computer vision. And thanks to transfer learning and amazing learning resources, anyone can start getting state of the art results within days and even hours, by using a pre-trained model and adapting it to your domain. …

Make your use of Vim more efficient — Background: Why You Should Give Vim a Try I recently started using Vim, and I don’t regret it. I quickly fell in love with its efficiency and power. …

This series provides overview of some of the prominent neural network architectures. Reading through this guide and all supplement materials will help you develop understanding of the modern neural network architectures and main ideas behind them. Before starting, you should have some familiarity with the basics of neural networks, backpropagation…

AlexNet [2012, paper by Krizhevsky et al.] — Main ideas ReLU nonlinearity, training on multiple GPUs, local response normalization, overlapping pooling, data augmentation, dropout Why it is important AlexNet won the ImageNet competition in 2012 by a large margin. It was the biggest network at the time. The network demonstrated the potential of training large neural networks quickly on massive datasets using widely available…

LeNet-5 [1998, paper by LeCun et al.] — Main Ideas convolution, local receptive fields, shared weights, spacial subsampling Why it is important LeNet-5 was used on large scale to automatically classify hand-written digits on bank cheques in the United States. This network is a convolutional neural network (CNN). CNNs are the foundation of modern state-of-the art deep learning-based computer vision. These networks are built…

Update: you can now enjoy this post on my personal blog, where math typography is much better (Medium doesn’t support math rendering, despite numerous requests). In this article, I will discuss two interesting recent papers that provide an easy way to improve performance of any given neural network by using…

Part of Understanding Hinton’s Capsule Networks Series: Part I: Intuition Part II: How Capsules Work Part III: Dynamic Routing Between Capsules Part IV: CapsNet Architecture (you are reading it now) Quick announcement about our new publication AI³. We are getting the best writers together to talk about the Theory, Practice, and Business of AI and machine learning…

Part of Understanding Hinton’s Capsule Networks Series: Part I: Intuition Part II: How Capsules Work Part III: Dynamic Routing Between Capsules (you are reading it now) Part IV: CapsNet Architecture Quick announcement about our new publication AI³. We are getting the best writers together to talk about the Theory, Practice, and Business of AI and machine learning…

Part of Understanding Hinton’s Capsule Networks Series: Part I: Intuition Part II: How Capsules Work (you are reading it now) Part III: Dynamic Routing Between Capsules Part IV: CapsNet Architecture Quick announcement about our new publication AI³. We are getting the best writers together to talk about the Theory, Practice, and Business of AI and machine learning…