5971
Deep Reinforcement Learning: Pong from Pixels
Musings of a Computer Scientist.
New
The latest blog posts to take off on Hacker News. 6,337 posts.
5972
Our Hybrid lda2vec Algorithm
The goal of lda2vec is to make volumes of text useful to humans (not machines!) while still keeping the model simple to modify. It learns the powerful word r...
5973
5974
Autoencoding Blade Runner: reconstructing films with artificial neural networks
Reconstructing films with artificial neural networks
5975
Fizz Buzz in Tensorflow
interviewer: Welcome, can I get you coffee or anything? Do you need a break? me: No, I've probably had too much coffee already! interviewer: Great, great. And are you OK with writing code on the...
5976
5977
5978
Google supercharges machine learning tasks with TPU custom chip
Machine learning provides the underlying oomph to many of Google’s most-loved applications. In fact, more than 100 teams are currently using machine learning at Google today, from Street View, to Inbox Smart Reply, to voice search.
5979
5980
Singular Value Decomposition Part 2: Theorem, Proof, Algorithm
I’m just going to jump right into the definitions and rigor, so if you haven’t read the previous post motivating the singular value decomposition, go back and do that first. This post will be theorem, proof, algorithm, data. The data set we test on is a thousand-story CNN news data set. All of the data, code, and…
5981
SyntaxNet in Context: Understanding Google's New TensorFlow NLP Model
Yesterday, Google open sourced their Tensorflow-based dependency parsing library, SyntaxNet. The library gives access to a line of neural network parsing models published by Google researchers over the last two years. I've been following this work closely since it was published, and have been looking forward to the…
5982
5983
Finding Similar Music Using Matrix Factorization
In a previous post I wrote about how to build a ‘People Who Like This Also Like …’ feature for displaying lists of similar musicians. My goal was to show how simple Information Retrieval techniques can do a good job calculating lists of related artists. For instance, using BM25 distance on The Beatles shows the most…
5984
Introducing FBLearner Flow: Facebook's AI Backbone
Visit the post for more.
5985
5986
Number plate recognition with Tensorflow
Over the past few weeks I’ve been dabbling with deep learning, in particular convolutional neural networks . One standout paper from recent times is Google’s Multi-digit Number Recognition from Street View . This paper describes a system for extracting house numbers from street view imagery using a single end-to-end…
5987
Deep Language Modeling for Question Answering Using Keras
Search BenchGecko research notes, methodology pages, benchmark sources, model rankings, pricing, compute, and company intelligence.
5988
5989
Neural Networks Are Impressively Good at Compression
I’m trying to get into neural networks. There have been a couple big breakthroughs in the field in recent years and suddenly my side project of messing around with programming languages seeme…
5990
DeepMind moves to TensorFlow
Posted by Koray Kavukcuoglu, Research Scientist, Google DeepMindAt DeepMind, we conduct state-of-the-art research on a wide range of algorithms, fr...
5991
A Deep Learning USB Stick
Unlock more with Intel Core Ultra processors. Experience superior AI performance, all-day battery life, and pro-level graphics for work and play.
5992
Markov Chain Monte Carlo Sampling
📍 This article has moved. Read the current version at This is the third part in a short series of blog posts about quantum Monte Carlo (QMC). The series is derived from an introductory lecture I ga…
5993
5994
How Kalman Filters Work
This articles describes how Kalman filters and other state estimation techniques work, focusing on building intuition and pointing out good implementation techniques.
5995
5996
Jarvis: an Amazon Echo clone in your browser
Javascript and Node.js training and consulting. Get your team up to speed fast or have us build and implement your next web application.
5997
5998
5999
Building an IBM Watson-powered AI Chatbot in 50 lines of code
Developing a speech-to-text bot using IBM’s Supercomputer.
6000