121
OpenAI Five Benchmark
Stay up to speed on the rapid advancement of AI technology and the benefits it offers to humanity.
New
The latest blog posts to take off on Hacker News. 292 posts.
122
Reproducible machine learning with PyTorch and Quilt
In this article, we'll use Quilt to transfer versioned training data to a remote machine. We'll start with the Berkeley Segmentation Dataset, package the dataset, then train a PyTorch model for super-resolution imaging.
123
Improving Connectomics by an Order of Magnitude
Posted by Viren Jain, Research Scientist and Technical Lead and Michal Januszewski, Software Engineer, Connectomics at Google The field of connecto...
124
How should we evaluate progress in AI?
Improving artificial intelligence research with scientific testing, design practice, and meta-rational choice of methods and criteria
125
Measuring abstract reasoning in neural networks
Neural network-based models continue to achieve impressive results on longstanding machine learning problems, but establishing their capacity to reason about abstract concepts has proven difficult. Building on previous efforts to solve this important feature of general-purpose learning systems, our latest paper sets…
126
Building a Program Synthesizer
Build a program synthesis tool, to generate programs from specifications, in 20 lines of code using Rosette.
127
Troubling Trends in Machine Learning Scholarship
By Zachary C. Lipton* & Jacob Steinhardt* *equal authorship Originally presented at ICML 2018: Machine Learning Debates [arXiv link] Published in Communications of the ACM 1 Introduction Collectively, machine learning (ML) researchers are engaged in
128
Glow: Better Reversible Generative Models
Stay up to speed on the rapid advancement of AI technology and the benefits it offers to humanity.
129
An AI system for editing music in videos
Given a video of a musical performance, CSAIL’s deep-learning system can make individual instruments louder or softer.
130
131
Augmenting Long-term Memory
One day in the mid-1920s, a Moscow newspaper reporter named Solomon Shereshevsky entered the laboratory of the psychologist Alexander Luria. Shereshevsky's boss at the newspaper had noticed that Shereshevsky never needed to take any notes, but somehow still remembered all he was told, and had suggested he get his…
132
Learning ‘Montezuma’s Revenge’ from a single demonstration
Stay up to speed on the rapid advancement of AI technology and the benefits it offers to humanity.
133
134
A New Angle on L2 Regularization
Deep neural networks have been shown to be vulnerable to the adversarial example phenomenon: all models tested so far can have their classifications dramatically altered by small image perturbations . The following predictions were for instance made by a state-of-the-art network trained to recognize celebrities :
135
136
An Easier Way to Build Alexa Skills Using Python
Amazon Apps & Services Developer Portal
137
The Matrix Calculus You Need for Deep Learning
Most of us last saw calculus in school, but derivatives are a critical part of machine learning, particularly deep neural networks, which are trained by optimizing a loss function. This article is an attempt to explain all the matrix calculus you need in order to understand the training of deep neural networks. We…
138
139
Keras vs PyTorch
Keras and PyTorch are both excellent choices for your first deep learning framework. Learn how they differ and which one will suit your needs better.
140
AI Can Detect Illnesses in Human Breath
Researchers from Loughborough University, Western General Hospital, the University of Edinburgh, and the Edinburgh Cancer Centre in the United Kingdom, recently developed a deep learning-based method…
141
Self-Supervised Tracking via Video Colorization
Posted by Carl Vondrick, Research Scientist, Machine Perception Tracking objects in video is a fundamental problem in computer vision, essential to...
142
Deep code search
Deep code search Gu et al., ICSE’18 The problem with searching for code is that the query, e.g. “read an object from xml,” doesn’t look very much like the source code snippets tha…
143
Ways to think about machine learning
Everyone has heard of machine learning now, and every big company is working on projects around ‘AI’. We know this is a Next Big Thing. But we don’t yet have a settled sense of quite what machine learning means - what it will mean for tech companies or for companies in the broader economy, how to
144
OpenAI Five
Stay up to speed on the rapid advancement of AI technology and the benefits it offers to humanity.
145
Neanderthal vs. ND4J – Native Performance, Java and CPU
Today, Java has a choice of a few well maintained libraries that can use Intel's MKL for fast native operations. MKL is basically as fast as you can get toda...
146
Improving Deep Learning Performance with AutoAugment
Posted by Ekin Dogus Cubuk, Google AI Resident and Barret Zoph, Research Scientist, Google Brain Team The success of deep learning in computer vi...
147
Debugging with intelligence via probabilistic inference
Debugging with intelligence via probabilistic inference Xu et al., ICSE’18 Xu et al. have built a automated debugger that can take a single failing test execution, and with minimal interactio…
148
149
Face recognition in images and video with Python
Learn how to perform face recognition using OpenCV, Python, and dlib by applying deep learning for highly accurate facial recognition.
150
