A Roundup of OpenAI's Active Work This Week
Spinning Up in Deep RL
OpenAI released Spinning Up in Deep RL, an educational resource designed to let anyone learn to become a skilled practitioner in deep reinforcement learning. Spinning Up consists of crystal-clear examples of RL code, educational exercises, documentation, and tutorials.
Learning Concepts with Energy Functions
OpenAI has developed an energy-based model that can quickly learn to identify and generate instances of concepts, such as near, above, between, closest, and furthest, expressed as sets of 2d points.
Reinforcement Learning with Prediction-Based Rewards
OpenAI developed Random Network Distillation (RND), a prediction-based method for encouraging reinforcement learning agents to explore their environments through curiosity, which for the first time exceeds average human performance on Montezuma’s Revenge.
Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control
OpenAI proposed a “plan online and learn offline” framework for the setting where an agent, with an internal model, needs to continually act and learn in the world. Their work builds on the synergistic relationship between local model-based control, global value function learning, and exploration
Serving ML Quickly with TensorFlow Serving and Docker
Serving machine learning models quickly and easily is one of the key challenges when moving from experimentation into production. To this end, one of the easiest ways to serve machine learning models is by using TensorFlow Serving with Docker. Docker is a tool that packages software into units called containers that include everything needed to run the software.
FloWaveNet: A Generative Flow for Raw Audio
FloWaveNet is a flow-based generative model that can do a real-time waveform audio synthesis. The main advantage of this approach we think is a real-time waveform synthesis as well as a single-stage, single loss training, unlike the Parallel WaveNet or ClariNet.
Seeing Through Walls with Adversarial WiFi Sensing: Attack and Defence Strategies?
Researchers from the University of California, Santa Barbara, and the University of Chicago have published a paper which identifies the risk of bad actors using smartphones’ WiFi signals to “see” through walls and surreptitiously track humans in their private rooms and offices.
You May Also Like
Seven Sectors Where AI Can Make Transformative Changes In China
In a Politburo group study session last week Chinese President Xi Jinping identified seven sectors where AI promises huge potential, asserting “AI is a key driving force of the new round of scientific revolution and industrial reform.”
DeepMind Announces Pre-Symptom Eye Disease Prediction at Moorfields
Google DeepMind has announced that its project with London’s Moorfields Eye Hospital will now include working with clinicians to predict eye diseases before symptoms occur.
Global AI Events
|11-16 Nov||TDWI Orlando Conference||Orlando, USA|
|13-14 Nov||Predictive Analytics World||Berlin, Germany|
|13–15 Nov||AI Summit||Cape Town, South Africa|
|14–16 Nov||Big Data Spain||Madrid,Spain|
|15–16 Nov||Future Technologies Conference 2018.||Vancouver, Canada.|
|21–22 Nov||Big Data & Analytics Innovation Summit.||Beijing, China|