A Guide to Understanding Convolutional Neural Networks (CNNs) using Visualization
Introduction “How did your neural network produce this result?” This question has sent many data scientists into a tizzy. It’s easy to explain how …
neural networks
DataHack Radio #15: Exploring the Applications & Potential of Reinforcement Learning with Xander Steenbrugge
Introduction “If intelligence was a cake, supervised learning would be the icing on the cake, and reinforcement learning would be the cherry on the …
An Introductory Guide to Deep Learning and Neural Networks (Notes from deeplearning.ai Course #1)
This is a comprehensive introduction to the world of deep learning and neural networks. These are essentially course notes from deeplearning.ai’s course #1.
Heroes of Deep Learning: Top Takeaways for Aspiring Data Scientists from Andrew Ng’s Interview Series
This article lists down the key takeaways for data scientists from Andrew Ng’s inspirational interview series with seven heroes of deep learning.
Perform Automated Machine Learning for Free with Microsoft’s Open Source Python Toolkit
Microsoft has open sourced a toolkit for automated machine learning called Neural Network Intelligence (NNI). It works with Python 3.5 or greater.
Rosetta – How Facebook uses Machine Learning to Process Text in Billions of Images
Facebook’s researchers have revealed how they use ML to process text from billions of images each day to provide an enriching user experience.
MIT Open Sources Computer Vision Model that Teaches Itself Object Detection in 45 Minutes (with GitHub codes)
MIT Researchers have developed a machine learning model that uses computer vision techniques to detect, and pick up objects in under an hour.
MIT’s Neural Network uses Text & Audio to Perform Sentiment Analysis for Healthcare
MIT researchers have designed a neural network model that uses text and audio recordings of natural conversations to diagnose depression.
DeepMind Open Sources Dataset to Measure the Reasoning Ability of Neural Networks
DeepMind have attempted to measure the reasoning ability of neural networks to understand the nature of generalization (dataset + paper links included).
Dactyl – OpenAI’s Robot Hand trained itself without any Human Learning (Video + Research Paper)
Dactyl is an OpenAI trained robot hand that can manipulate objects with mind boggling dexterity. Check out the incredible video and research paper inside.
