We're releasing an analysis showing that since 2012, the amount of compute used in the largest AI training runs has been increasing exponentially with a 3.5 month-doubling time (by comparison, Moore's Law had an 18-month doubling period). Since 2012, this metric has grown by more than 300,000x (an 18-month doubling period would yield only a 12x increase). Improvements in compute have been a key component of AI progress, so as long as this trend continues, it's worth preparing for the implications of systems far outside today's capabilities. The chart shows the total amount of compute, in petaflop/s-days, that was used to train selected results that are relatively well known, used a lot of compute for their time, and gave enough information to estimate the compute used. A petaflop/s-day (pfs-day) consists of performing 1015 neural net operations per second for one day, or a total of about 1020 operations.

This is a talk by Ilya Sutskever for course 6.S099: Artificial General Intelligence. He is the Co-Founder of OpenAI. This class is free and open to everyone. Our goal is to take an engineering approach to exploring possible paths toward building human-level intelligence for a better world.

Reinforcement learning (RL) is hot! It allows programmers to create software agents that learn to take optimal actions to maximize reward, through trying out different strategies in a given environment. This course will take you through all the core concepts in Reinforcement Learning, transforming a theoretical subject into tangible Python coding exercises with the help of OpenAI Gym. The videos will first guide you through the gym environment, solving the CartPole-v0 toy robotics problem, before moving on to coding up and solving a multi-armed bandit problem in Python. As the course ramps up, it shows you how to use dynamic programming and TensorFlow-based neural networks to solve GridWorld, another OpenAI Gym challenge.

Researchers at OpenAI have already proven AI can get really good at video games. Now they are teaching AI how to learn games quickly, like a human would. That's why they've challenged developers to submit their own code for an AI-only Sonic the Hedgehog competition. For more videos, subscribe to Mashable Daily: http://on.mash.to/SubscribeNews Give us a follow: Facebook: https://www.facebook.com/mashable/

We're proposing an AI safety technique which trains agents to debate topics with one another, using a human to judge who wins. We believe that this or a similar approach could eventually help us train AI systems to perform far more cognitively advanced tasks than humans are capable of, while remaining in line with human preferences. We're going to outline this method together with preliminary proof-of-concept experiments and are also releasing a web interface so people can experiment with the technique. The debate method visualized as a game tree, similar to a game like Go but with sentences between debaters for moves and human judgements at leaf nodes. In both debate and Go, the true answer depends on the entire tree, but a single path through the tree chosen by strong agents is evidence for the whole.

Someday, it might be perfectly normal to watch an AI system fight with itself. The concept comes from researchers at OpenAI, a nonprofit founded by several Silicon Valley luminaries, including Y Combinator partner Sam Altman, LinkedIn chair Reid Hoffman, Facebook board member and Palantir founder Peter Thiel, and Tesla and SpaceX head Elon Musk. The OpenAI researchers have previously shown that AI systems that train themselves can sometimes develop unexpected and unwanted habits. For example, in a computer game, an agent may figure out how to "glitch" its way to a higher score. In some cases it may be possible for a person to supervise the training process.

Q-learning (which doesn't stand for anything, by the way) is centered around creating a "virtual table" that accounts for how much reward is assigned to each possible action given the current state of the environment. Let's break that down one step at a time: What do we mean by "virtual table?" Imagine that for each possible configuration of the input space, you have a table that assigns a score for each of the possible actions you can take. If this were magically possible, then it would be extremely easy for you to "beat" the environment: simply choose the action that has the highest score! Two points to note about this score.

Although machine learning has been successfully used to propose novel molecules that satisfy desired properties, it is still challenging to explore a large chemical space efficiently. In this paper, we present a conditional molecular design method that facilitates generating new molecules with desired properties. The proposed model, which simultaneously performs both property prediction and molecule generation, is built as a semi-supervised variational autoencoder trained on a set of existing molecules with only a partial annotation. We generate new molecules with desired properties by sampling from the generative distribution estimated by the model. We demonstrate the effectiveness of the proposed model by evaluating it on drug-like molecules. The model improves the performance of property prediction by exploiting unlabeled molecules, and efficiently generates novel molecules fulfilling various target conditions.

This work exploits translation data as a source of semantically relevant learning signal for models of word representation. In particular, we exploit equivalence through translation as a form of distributed context and jointly learn how to embed and align with a deep generative model. Our EmbedAlign model embeds words in their complete observed context and learns by marginalisation of latent lexical alignments. Besides, it embeds words as posterior probability densities, rather than point estimates, which allows us to compare words in context using a measure of overlap between distributions (e.g. KL divergence). We investigate our model's performance on a range of lexical semantics tasks achieving competitive results on several standard benchmarks including natural language inference, paraphrasing, and text similarity.

Researchers in artificial intelligence can stand to make a ton of money. But this week, we actually know just how much some A.I. experts are being paid -- and it's a lot, even at a nonprofit. OpenAI, a nonprofit research lab, paid its lead A.I. expert, Ilya Sutskever, more than $1.9 million in 2016, according to a recent public tax filing. Another researcher, Ian Goodfellow, made more than $800,000 that year, even though he was only hired in March, the New York Times reported. As the publication points out, the figures are eye-opening and offer a bit of insight on how much A.I. researchers are being paid across the globe.