241
242
Zero-shot learning: Using text to more accurately identify images
WHAT THE RESEARCH IS: Zero-shot learning (ZSL) is a process by which a machine learns to recognize objects it has never seen before. Researchers at Facebook have developed a new, more accurate ZSL …
243
244
Facebook AI Research Expands with New Academic Collaborations
This article originally appeared on newsroom.fb.com. We created Facebook AI Research over four years ago to focus on advancing the science and technology of AI, and we’ve always done this by…
245
Mozilla Announces $225,000 for Art and Advocacy Exploring A.I.
Mozilla’s latest awards will support people and projects that examine the effects of AI on society At Mozilla, one way we support a healthy internet i
246
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...
247
248
An Augmented Reality Microscope for Cancer Detection
Posted by Martin Stumpe, Technical Lead and Craig Mermel, Product Manager, Google Brain Team (Updated Aug 12, 2019: The work described in this blog...
249
250
Interactive computational neuroscience – part 1, spiking neurons
An interactive introduction to spiking neuron models -- all in the browser. Learn about modeling neurons as dynamical systems and the computational properties of neurons.
251
Intro to Quantum Information Science
Someone recently wrote that my blog is “too high on nerd whining content and too low on actual compsci content to be worth checking too regularly.” While that’s surely one of the…
252
253
OpenAI Supporters
Stay up to speed on the rapid advancement of AI technology and the benefits it offers to humanity.
254
Faster R-CNN: Down the rabbit hole of modern object detection
In this post, I'll explain the architecture of Faster R-CNN, starting with a high level overview, and then go over the details for each of the components. You'll be introduced to base networks, anchors as well as the region proposal network.
255
256
257
258
259
260
3D Face Reconstruction with Position Map Regression Networks
Position Map Regression Networks (PRN) is a method to jointly regress dense alignment and 3D face shape in an end-to-end manner. In this article, I’ll provide a short explanation and discuss its applications in computer vision. When I was a… Continue reading 3D Face Reconstruction with Position Map Regression Networks
261
Algorithm efficiency comes from problem information
This is a high level post about algorithms (especially mathematical, scientific, and data analysis algorithms) which I hope can help people who are not researchers or numerical software developers better understand how to choose and evaluate algorithms. When scientists and programmers think about efficiency of…
262
Empiricism and the limits of gradient descent
This post is actually about artificial intelligence, and argues a position that many AI researchers will disagree with. Specifically, it arg...
263
264
265
Using Self-Organizing Maps to Solve the Traveling Salesman Problem
Using Self-Organizing Maps to solve the Traveling Salesman Problem The Traveling Salesman Problem is a well known challenge in Computer Science: it consists on finding the shortest route possible that traverses all cities in a given map only once. Although its simple explanation, this problem is, indeed, NP-Complete…
266
Why Can a Machine Beat Mario but Not Pokemon?
Why Can a Machine Beat Mario but not Pokemon? By now, you’ve probably heard of bots playing video games at superhuman levels. These bots can be programmed explicitly, reacting to set inputs with …
267
268
The International 2018: Results
Stay up to speed on the rapid advancement of AI technology and the benefits it offers to humanity.
269
Grasp2Vec: Learning Object Representations from Self-Supervised Grasping
Posted by Eric Jang, Software Engineer, Robotics at Google and Coline Devin, Berkeley PhD Student and former Research Intern From a remarkably youn...
270
Train TensorFlow models faster and at lower cost on Cloud TPU Pods
TPUs provide a faster and more cost-effective way to train machine learning models. Learn more about the benefits of training models on Cloud TPU Pods.