|
|
January 15 · Issue #74 · View online
The Wild Week in AI is a weekly AI & Deep Learning newsletter curated by @dennybritz.
|
|
If you enjoy the newsletter, please consider sharing it on Twitter, Facebook, etc! Really appreciate the support :)
|
|
|
Whisper.ai builds hearing aids which use deep learning to amplify only the voices and sounds of interest in <10ms realtime. Whisper has 10x the noise reduction of existing products, has the Apple AirPods architect leading hardware, is well-funded by Sequoia Capital, and is working to help +360MM people hear clearly again. Technical problems include mapping spectrograms to a separable embedding space, model compression, perceptual/adversarial loss functions, and embedded hardware optimization. We’re a small team looking for top engineers excited to advance audio deep learning and help redefine a human sense. You can apply here or email us directly at jobs@whisper.ai.
|
|
Facebook is shutting down its standalone personal assistant “M”
M users received messages that Facebook is sunsetting the service on January 19th. Even though it was branded as AI, behind the scenes M relied on humans to answer the most complicated queries. For instance, you could book a table at a restaurant, order flowers or organize your next vacation.
|
Yann LeCun calls SingularyNET 's robot Sophia B.S.
Ben Goertzel, CEO and chief scientist at Sophia’s creator SingularyNET, said he has never pretended Sophia has human capabilities, but SingularityNET chairman David Hanson has described Sophia as “basically alive”.
|
Leave A.I. Alone
This piece argues that current approach to AI regulation, pushed by people such as Elon Musk, is a mistake. We’ve already regulated AI it in the past. We just didn’t call it AI.
|
The Google Brain Team - Looking Back on 2017
This two-part series reviews what the Google Brain team has been up to in 2017. It’s also a good general overview of research advances from the past year.
|
PyImageConf 2018: Practical Computer Vision conference
A new conference, PyImageConf 2018 will be taking place August 26-28th at the San Francisco Hyatt Regency.
|
|
Introduction to Reinforcement Learning Algorithms Part 1
This post covers Reinforcement Learning (RL) basics and the popular Q-Learning, SARSA, DQN, and DDPG algorithms.
|
Ray: A Distributed System for AI
One of Ray’s goals is to enable practitioners to turn a prototype algorithm that runs on a laptop into a high-performance distributed application that runs efficiently on a cluster.
|
Deep Learning Skepticism
|
One Model to Learn Them All: Paper Review
Deep neural networks are typically designed and tuned for the problem at hand. Can we create a unified deep learning model to solve tasks across multiple domains?
|
|
Turning Design Mockups Into Code With Deep Learning
Train neural network to code a basic a HTML and CSS website based on a picture of a design mockup. All the code is available on Github.
|
MuJoCo Plugin and Unity Integration for Reinforcement Learning
The goal of the MuJoCo Plugin and Unity Integration package is to combine the best of both worlds: use MuJoCo physics and Unity rendering within the same project.
|
A Tensorflow implementation of Capsule Networks
|
|
[1801.03526] Neural Program Synthesis with Priority Queue Training
The authors consider the task of program synthesis in the presence of a reward function over the output of programs, where the goal is to find programs with maximal rewards. Their PQT algorithm outperforms the baselines. By adding a program length penalty to the reward function, the authors can synthesize short, human-readable programs.
|
[1801.03244] eCommerceGAN : A Generative Adversarial Network for E-commerce (Amazon)
A Generative Adversarial Network (GAN) for orders made in e-commerce websites. Once trained, the generator in the GAN could generate any number of plausible orders.
|
[1801.03326] Expected Policy Gradients for Reinforcement Learning
Expected policy gradients (EPG) unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning. EPG integrates (or sums) across actions when estimating the gradient, instead of relying only on the action in the sampled trajectory.
|
[1801.01290] Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
The authors propose soft actor-critic, an off-policy actor-critic deep RL algorithm based on the maximum entropy reinforcement learning framework. In this framework, the actor aims to maximize expected reward while also maximizing entropy - that is, succeed at the task while acting as randomly as possible.
|
Did you enjoy this issue?
|
|
|
|
In order to unsubscribe, click here.
If you were forwarded this newsletter and you like it, you can subscribe here.
|
|
|