Author Archives: David Calloway
DeepMind AI Masters Stratego
Stratego is a popular board game that involves strategy and deception. Players take turns moving their pieces, with the goal of capturing their opponent’s flag or trapping their opponent’s pieces. It is a challenging game that requires players to think … Continue reading
Deep Reinforcement Learning for AI Chip Design
A team from Google Brain recently published a paper (on arXiv) describing the use of a Deep Reinforcement Learning algorithm to design chips customized for AI applications. In other words, they used an AI to build AI chips. The problem … Continue reading
TensorFlow or PyTorch: Which Framework to Choose?
I was recently asked by Udacity to be a beta tester (and, subsequently, a mentor and project reviewer) for one of their newest course offerings: the Deep Reinforcement Learning NanoDegree (DRLND) program. This is a very interesting course with some … Continue reading
Nvidia Announces Apex: A New PyTorch Extension
Nvidia recently announced a new, open-source PyTorch extension that helps users improve the performance of deep learning training on Nvidia’s Volta GPUs. The key improvement that APEX brings to deep learning is that it enables engineers to use mixed precision … Continue reading
IBM Debater
IBM just demonstrated a deep-learning system that is a follow-on of sorts to the Watson Jeopardy demonstration from several years ago. For this IBM Debater project, Watson was trained to intelligently debate on approximately 100 different topics. In this particular … Continue reading
The h Index & the Top 15 Deep Learning Conferences and Journals
The Google Scholar resource ranks the top journals and conferences using a fully automated h-index score. The h-index is named after Jorge Hirsch, a physicist at the University of California, San Diego (UCSD), who proposed the index to determine theoretical … Continue reading
MIT’s RoadTracer Uses Deep Learning to Generate Road Networks from Satellite Imagery
The CSAIL group at the Massachusetts Institute of Technology (MIT) have improved the state-of-the art in inferring road networks from satellite imagery. This is a time-consuming, tedious, and error-prone process that has traditionally relied on human inputs. Open Street Map … Continue reading
Deep Reinforcement Learning for Navigation
A recent Nature article (https://go.nature.com/2GdzegP) and accompanying blog post by the paper’s authors (https://deepmind.com/blog/grid-cells/) describes how the Andrea Banino et. al. from Deep Mind developed an artificial neural network to investigate how mammals use neural grid cells to perform vector-based navigation. … Continue reading
Google Duplex – I’m Pretty Amazed!
One of the things that we often see in Sci-Fi movies, but rarely experience in real life, is the ability to have a natural conversation with a computer. Rapid advances in AI and deep learning in recent years have brought … Continue reading
Nvidia Quadro GV100 – A Deep Learning Supercomputer on a Card
At this year’s GPU Technology Conference (Mar 28-30, 2018), Nvidia announced a new GPU specifically designed for deep learning. The Quadro GV100, based on Nvidia’s latest Volta architecture, sports 5120 CUDA cores, 640 tensor cores, and 32GB of VRAM – … Continue reading