Estimating the perfect times for drivers to pick up food delivery orders for a number of different restaurants can be one of the most difficult of computational problems. Think of it like the Traveling Salesperson NP-Hard combinatorial optimization problem: The customer wants food delivered in a timely manner, and the delivery person wants to food ready when they roll-up. If the estimates are off by even a tiny bit, then customers are unhappy and delivery people will work elsewhere. Yet, car-sharing service Uber is building a global service, called Uber Eats, that will rely on accurate predictions to succeed. The secret to its success will be machine learning, built from the company's in-house ML platform, nicknamed Michelangelo.

We present SentiMATE, a novel end-to-end Deep Learning model for Chess, employing Natural Language Processing that aims to learn an effective evaluation function assessing move quality. This function is pre-trained on the sentiment of commentary associated with the training moves and is used to guide and optimize the agent's game-playing decision making. The contributions of this research are three-fold: we build and put forward both a classifier which extracts commentary describing the quality of Chess moves in vast commentary datasets, and a Sentiment Analysis model trained on Chess commentary to accurately predict the quality of said moves, to then use those predictions to evaluate the optimal next move of a Chess agent. Both classifiers achieve over 90 % classification accuracy. Lastly, we present a Chess engine, SentiMATE, which evaluates Chess moves based on a pre-trained sentiment evaluation function. Our results exhibit strong evidence to support our initial hypothesis - "Can Natural Language Processing be used to train a novel and sample efficient evaluation function in Chess Engines?" - as we integrate our evaluation function into modern Chess engines and play against agents with traditional Chess move evaluation functions, beating both random agents and a DeepChess implementation at a level-one search depth - representing the number of moves a traditional Chess agent (employing the alpha-beta search algorithm) looks ahead in order to evaluate a given chess state.

One-Shot Neural architecture search (NAS) attracts broad attention recently due to its capacity to reduce the computational hours through weight sharing. However, extensive experiments on several recent works show that there is no positive correlation between the validation accuracy with inherited weights from the supernet and the test accuracy after re-training for One-Shot NAS. Different from devising a controller to find the best performing architecture with inherited weights, this paper focuses on how to sample architectures to train the supernet to make it more predictive. A single-path supernet is adopted, where only a small part of weights are optimized in each step, to reduce the memory demand greatly. Furthermore, we abandon devising complicated reward based architecture sampling controller, and sample architectures to train supernet based on novelty search. An efficient novelty search method for NAS is devised in this paper, and extensive experiments demonstrate the effectiveness and efficiency of our novelty search based architecture sampling method. The best architecture obtained by our algorithm with the same search space achieves the state-of-the-art test error rate of 2.51\% on CIFAR-10 with only 7.5 hours search time in a single GPU, and a validation perplexity of 60.02 and a test perplexity of 57.36 on PTB. We also transfer these search cell structures to larger datasets ImageNet and WikiText-2, respectively.

It is typical for a machine learning system to have numerous hyperparameters that affect its learning rate and prediction quality. Finding a good combination of the hyperparameters is, however, a challenging job. This is mainly because evaluation of each combination is extremely expensive computationally; indeed, training a machine learning system on real data with just a single combination of hyperparameters usually takes hours or even days. In this paper, we address this challenge by trying to predict the performance of the machine learning system with a given combination of hyperparameters without completing the expensive learning process. Instead, we terminate the training process at an early stage, collect the model performance data and use it to predict which of the combinations of hyperparameters is most promising. Our preliminary experiments show that such a prediction improves the performance of the commonly used random search approach.

Personalized Route Recommendation (PRR) aims to generate user-specific route suggestions in response to users' route queries. Early studies cast the PRR task as a pathfinding problem on graphs, and adopt adapted search algorithms by integrating heuristic strategies. Although these methods are effective to some extent, they require setting the cost functions with heuristics. In addition, it is difficult to utilize useful context information in the search procedure. To address these issues, we propose using neural networks to automatically learn the cost functions of a classic heuristic algorithm, namely A* algorithm, for the PRR task. Our model consists of two components. First, we employ attention-based Recurrent Neural Networks (RNN) to model the cost from the source to the candidate location by incorporating useful context information. Instead of learning a single cost value, the RNN component is able to learn a time-varying vectorized representation for the moving state of a user. Second, we propose to use a value network for estimating the cost from a candidate location to the destination. For capturing structural characteristics, the value network is built on top of improved graph attention networks by incorporating the moving state of a user and other context information. The two components are integrated in a principled way for deriving a more accurate cost of a candidate location. Extensive experiment results on three real-world datasets have shown the effectiveness and robustness of the proposed model.

Pluribus is the first AI bot capable of beating human experts in six-player no-limit Hold'em, the most widely played poker format in the world. This is the first time an AI bot has beaten top human players in a complex game with more than two players or two teams. We tested Pluribus against professional poker players, including two winners of the World Series of Poker Main Event. Pluribus succeeds because it can very efficiently handle the challenges of a game with both hidden information and more than two players. It uses self-play to teach itself how to win, with no examples or guidance on strategy. Pluribus uses far fewer computing resources than the bots that have defeated humans in other games. The bot's success will advance AI research, because many important AI challenges involve many players and hidden information. For decades, poker has been a difficult and important grand challenge problem for the field of AI. Because poker involves hidden information -- you don't know your opponents' cards -- success requires bluffing and other strategies that do not apply to chess, Go, and other games.

"The solution to the Rubik's Cube involves more symbolic, mathematical and abstract thinking, so a deep learning machine that can crack such a puzzle is getting closer to becoming a system that can think, reason, plan and make decisions." An expert system designed for a narrow task, such as only solving a Rubik's Cube will forever be limited to that domain. But a system like DeepCubeA, boasting an adaptable neural net, can be used for other tasks, such as solving complex scientific, mathematical, and engineering problems. Stephen McAleer, a co-author of the new paper, told Gizmodo how this system "is a small step toward creating agents that are able to learn how to think and plan for themselves in new environments." Reinforcement learning works the way it sounds.

The human record for solving a Rubik's Cube has been smashed by an artificial intelligence. The bot, called DeepCubeA, completed the popular puzzle in a fraction of a second - much faster than the quickest humans. While algorithms have previously been developed specifically to solve the Rubik's Cube, this is the first time it has done without any specific domain knowledge or in-game coaching from humans. It brings researchers a step closer to creating an advanced AI system that can think like a human. "The solution to the Rubik's Cube involves more symbolic, mathematical and abstract thinking," said senior author Professor Pierre Baldi, a computer scientist at the University of California, Irvine.

Researchers have developed an AI algorithm which can solve a Rubik's cube in a fraction of a second, according to a study published in the journal Nature Machine Intelligence. The system, known as DeepCubeA, uses a form of machine learning which teaches itself how to play in order to crack the puzzle without being specifically coached by humans. "Artificial intelligence can defeat the world's best human chess and Go players, but some of the more difficult puzzles, such as the Rubik's Cube, had not been solved by computers, so we thought they were open for AI approaches," Pierre Baldi, one of the developers of the algorithm and computer scientist from the University of California, Irvine, said in a statement. According to Baldi, the latest development could herald a new generation of artificial intelligence (AI) deep-learning systems which are more advanced than those used in commercially available applications such as Siri and Alexa. "These systems are not really intelligent; they're brittle, and you can easily break or fool them," Baldi said.

An artificial intelligence system created by researchers at the University of California has solved the Rubik's Cube in just over a second. DeepCubeA, as the algorithm was called, completed the 3D logic puzzle which has been taxing humans since it was invented in 1974. "It learned on its own," said report author Prof Pierre Baldi. The researchers noted that its strategy was very different from the way humans tackle the puzzle. "My best guess is that the AI's form of reasoning is completely different from a human's," said Prof Baldi, who is professor of computer science at University of California, Irvine.