|November 16 · Issue #15 · View online |
This week’s issue features a look into how facebook fosters and accelerates AI innovation, some great learning material on parallelism in machine learning and hierarchical object detection as well as a paper introducing a new approach to neural machine translation.
As always if you enjoy receiving this newsletter, please considering sharing it with friends and colleagues, your support is very much appreciated.
| Accelerating Innovation and Powering New Experiences with AI | Facebook Newsroom |
Facebook outlines its approach of turning the latest research breakthroughs into tools, platforms and infrastructure.
| High-performance computing with Machine Learning at Intel | The Information Age |
| Humanity and AI will be inseparable | Verge 2021 |
While some predict mass unemployment or all-out war between humans and artificial intelligence, others foresee a less bleak future.
| Research Blog: Enhance! RAISR Sharp Images with Machine Learning |
With “RAISR: Rapid and Accurate Image Super-Resolution”, Google Research introduces a technique that incorporates machine learning in order to produce high-quality versions of low-resolution images.
| Parallelism in Machine Learning: GPUs, CUDA, and Practical Applications |
An introductory overview to GPU-based parallelism, the CUDA framework, and some thoughts on practical implementation.
| Applying the deep learning techniques from Alpha Go to play tic-tac-toe |
AlphaToe - Applying the deep learning techniques from Alpha Go to play tic-tac-toe
| GitHub - worldofpiggy/deeplearning-ahem-detector |
The ahem detector is a deep convolutional neural network that is trained on transformed audio signals to recognize “ahem” sounds.
| GitHub - jakebian/quiver: Interactive convnet features visualization for Keras |
quiver - Interactive convnet features visualization for Keras
| A Convolutional Encoder Model for Neural Machine Translation |
The prevalent approach to neural machine translation relies on bi-directional LSTMs to encode the source sentence. In this paper the authors present a faster and conceptually simpler architecture based on a succession of convolutional layers.
| Hierarchical Object Detection with Deep Reinforcement Learning |
Deep Reinforcement Learning Workshop presenting a method for performing hierarchical object detection in images guided by a deep reinforcement learning agent.