151
Moving Camera, Moving People: A Deep Learning Approach to Depth Prediction
Posted by Tali Dekel, Research Scientist and Forrester Cole, Software Engineer, Machine Perception The human visual system has a remarkable abili...
New
The latest blog posts to take off on Hacker News. 262 posts.
152
153
Implementing a Convolutional Neural Network from Scratch in Python
A simple guide to what CNNs are, how they work, and how to build one from scratch in Python.
154
155
Notes on Weight Initialization for Deep Neural Networks
Neural networks involve long sequence of multiplications, usually between a matrix and a vector, say \(a*x\). The result of this sequence of multiplications will either have a huge magnitude or be reduced to 0. We can divide \(a\) by a number ( scaling_factor ) to scale down its magnitude to the right level. Proper…
156
Matrices as Tensor Network Diagrams
In the previous post, I described a simple way to think about matrices, namely as bipartite graphs. Today I'd like to share a different way to picture matrices—one which is used not only in mathematics, but also in physics and machine learning. Here's the basic idea. An $m\times n$ matrix $M$ with real entries…
157
Translatotron: An End-to-End Speech-to-Speech Translation Model
Posted by Ye Jia and Ron Weiss, Software Engineers, Google AI Speech-to-speech translation systems have been developed over the past several decade...
158
Neural nets typically contain smaller “subnetworks” that can often learn faster
MIT CSAIL's "Lottery ticket hypothesis" finds that neural networks typically contain smaller subnetworks that can be trained to make equally accurate predictions, and often much more quickly.
159
Microsoft makes AI tool for better search available as an open source project
Only a few years ago, web search was simple. Users typed a few words and waded through pages of results.
160
Fun with Snapchat's Gender Swapping Filter
Snapchat's new gender-bending filter is a source of endless fun and laughs at parties. The results are very pleasing to look at. As someone ...
161
Predicting Stack Overflow Tags with Google’s Cloud AI
Check out a cool project that leverages Stack Overflow Data and Google's Cloud AI to predict what tags would work best on Stack Overflow questions.
162
163
164
TensorFlow Graphics: Computer Graphics Meets Deep Learning
Posted by Julien Valentin and Sofien Bouaziz
165
166
Google’s Cloud TPU Pods are now publicly available in beta
Cloud TPU Pods are now available in beta, helping you train models faster and at lower cost in the cloud.
167
Smarter Training of Neural Networks
These days, nearly all the artificial intelligence-based products in our lives rely on “deep neural networks” that automatically learn to process labeled data.
168
OpenAI releases larger GPT-2 model
We’ve trained a large-scale unsupervised language model which generates coherent paragraphs of text, achieves state-of-the-art performance on many language modeling benchmarks, and performs rudimentary reading comprehension, machine translation, question answering, and summarization—all without task-specific training.
169
Open-Sourcing Ax and BoTorch: New AI Tools for Adaptive Experimentation
We are open-sourcing BoTorch and Ax, two new tools that leverage adaptive experimentation to efficiently tackle optimization challenges in tuning software configurations, machine learning hyperparameters, ranking systems, and more.
170
171
172
173
Speedgate: World’s First Sport Generated by AI
Developers from AKQA, a global innovation agency most known for working with some of the hottest brands and public figures, trained a recurrent neural network and a deep convolutional generative…
174
MuseNet
We’ve created MuseNet, a deep neural network that can generate 4-minute musical compositions with 10 different instruments, and can combine styles from country to Mozart to the Beatles. MuseNet was not explicitly programmed with our understanding of music, but instead discovered patterns of harmony, rhythm, and style…
175
A Recipe for Training Neural Networks
Musings of a Computer Scientist.
176
Notes on AI Bias
Machine learning is the new centre of tech, and like all big new things there are issues. ‘AI bias’ is much-discussed right now: machine learning finds patterns but sometimes it finds the wrong one, and it can be hard to tell.
177
Graph Convolutional Networks (2016)
Many important real-world datasets come in the form of graphs or networks: social networks, knowledge graphs, protein-interaction networks, the World Wide Web, etc. (just to name a few). Yet, until recently, very little attention has been devoted to the generalization of neural...
178
179
180
OpenCV-Python Cheat Sheet: From Importing Images to Face Detection
What is OpenCV-Python? OpenCV is an open source computer vision and machine learning library. It has 2500+ optimized algorithms—a comprehensive set of both classic and state-of-the-art computer vision and machine learning algorithms. It has many interfaces, including Python, Java, C++,… Continue reading OpenCV-Python…