We present a reinforcement learning (RL) based guidance system for automated theorem proving geared towards Finding Longer Proofs (FLoP). FLoP focuses on generalizing from short proofs to longer ones of similar structure. To achieve that, FLoP uses state-of-the-art RL approaches that were previously not applied in theorem proving. In particular, we show that curriculum learning significantly outperforms previous learning-based proof guidance on a synthetic dataset of increasingly difficult arithmetic problems.

Me: Alexa please remind me my morning yoga sculpt class is at 5:30am. Alexa: I have added Tequila to your shopping list. We talk to our devices, and sometimes they recognize what we are saying correctly. We use free services to translate foreign language phrases encountered online into English, and sometimes they give us an accurate translation. Although natural language processing has been improving by leaps and bounds, it still has considerable room for improvement.

In the economic game of survival of the fittest, reinvention is a constant theme. Where would Samsung be today if it still sold dried fish? For example, Uber is often mentioned as an example of an industry disruptor that displaced jobs for incumbent taxi drivers. However, a recent analysis of Uber's impact on U.S. cities showed that Uber not only increased the number of jobs for drivers by 50% on average, but the wages for Uber drivers were about 10% higher. The same is true for technological progress -- while it does disrupt the way things were done in the past, it also opens the door for new opportunities and skills.

Welcome to our HR Modernization Playbook: Tomorrow's people – Why HR matters more than ever in the age of artificial intelligence. Digital transformation is happening faster than ever. The adoption of artificial intelligence (AI) and automation will redefine jobs, enhance employee productivity and accelerate workforce development. In fact, skills and culture – not technology – are the biggest barriers to business growth in the AI era. This means CEOs are looking to their CHRO to lead culture change, manage talent and drive down costs.

He and his colleagues have built a device, about the size of a thin laptop, that emits sound at frequencies 10 times higher than the shrillest note a piccolo can sustain. The pitches it produces are inaudible to the human ear. When Guo's team aims the device at a person and fires an ultrasonic pitch, the gadget listens for the echo using its hundreds of embedded microphones. Then, employing artificial intelligence techniques, his team tries to decipher what the person is doing from the reflected sound alone. The technology is still in its infancy, but they've achieved some promising initial results.

Eight Microsoft interns have developed a new language learning tool that uses the smartphone camera to help adults improve their English literacy by learning the words for the things around them. The app, Read My World, lets you take a picture with your phone to learn from a library of more than 1,500 words. The photo can be of a real-world object or text found in a document, Microsoft says. The app is meant to either supplement formal classroom training or offer a way to learn some words for those who didn't have the time or funds to participate in a language learning class. Instead of lessons, users are encouraged to snap photos of the things they encounter in their everyday lives.

Although reinforcement learning (RL) can provide reliable solutions in many settings, practitioners are often wary of the discrepancies between the RL solution and their status quo procedures. Therefore, they may be reluctant to adapt to the novel way of executing tasks proposed by RL. On the other hand, many real-world problems require relatively small adjustments from the status quo policies to achieve improved performance. Therefore, we propose a student-teacher RL mechanism in which the RL (the "student") learns to maximize its reward, subject to a constraint that bounds the difference between the RL policy and the "teacher" policy. The teacher can be another RL policy (e.g., trained under a slightly different setting), the status quo policy, or any other exogenous policy. We formulate this problem using a stochastic optimization model and solve it using a primal-dual policy gradient algorithm. We prove that the policy is asymptotically optimal. However, a naive implementation suffers from high variance and convergence to a stochastic optimal policy. With a few practical adjustments to address these issues, our numerical experiments confirm the effectiveness of our proposed method in multiple GridWorld scenarios.

We provide an online convex optimization algorithm with regret that interpolates between the regret of an algorithm using an optimal preconditioning matrix and one using a diagonal preconditioning matrix. Our regret bound is never worse than that obtained by diagonal preconditioning, and in certain setting even surpasses that of algorithms with full-matrix preconditioning. Importantly, our algorithm runs in the same time and space complexity as online gradient descent. Along the way we incorporate new techniques that mildly streamline and improve logarithmic factors in prior regret analyses. We conclude by benchmarking our algorithm on synthetic data and deep learning tasks.

Achieving faster execution with shorter compilation time can enable further diversity and innovation in neural networks. However, the current paradigm of executing neural networks either relies on hand-optimized libraries, traditional compilation heuristics, or very recently, simulated annealing and genetic algorithms. Our work takes a unique approach by formulating compiler optimizations for neural networks as a reinforcement learning problem, whose solution takes fewer steps to converge. This solution, dubbed ReLeASE, comes with a sampling algorithm that leverages clustering to focus the costly samples (real hardware measurements) on representative points, subsuming an entire subspace. Our adaptive sampling not only reduces the number of samples, but also improves the quality of samples for better exploration in shorter time. As such, experimentation with real hardware shows that reinforcement learning with adaptive sampling provides 4.45x speed up in optimization time over AutoTVM, while also improving inference time of the modern deep networks by 5.6%. Further experiments also confirm that our adaptive sampling can even improve AutoTVM's simulated annealing by 4.00x.

The development of models for learning music similarity and feature extraction from audio media files is an increasingly important task for the entertainment industry. This work proposes a novel music classification model based on metric learning and feature extraction from MP3 audio files. The metric learning process considers the learning of a set of parameterized distances employing a structured prediction approach from a set of MP3 audio files containing several music genres. The main objective of this work is to make possible learning a personalized metric for each customer. To extract the acoustic information we use the Mel-Frequency Cepstral Coefficient (MFCC) and make a dimensionality reduction with the use of Principal Components Analysis. We attest the model validity performing a set of experiments and comparing the training and testing results with baseline algorithms, such as K-means and Soft Margin Linear Support Vector Machine (SVM). Experiments show promising results and encourage the future development of an online version of the learning model.