Transportation


Reinforcement Learning for Solving the Vehicle Routing Problem

Neural Information Processing Systems

We present an end-to-end framework for solving the Vehicle Routing Problem (VRP) using reinforcement learning. In this approach, we train a single policy model that finds near-optimal solutions for a broad range of problem instances of similar size, only by observing the reward signals and following feasibility rules. We consider a parameterized stochastic policy, and by applying a policy gradient algorithm to optimize its parameters, the trained model produces the solution as a sequence of consecutive actions in real time, without the need to re-train for every new problem instance. On capacitated VRP, our approach outperforms classical heuristics and Google's OR-Tools on medium-sized instances in solution quality with comparable computation time (after training). We demonstrate how our approach can handle problems with split delivery and explore the effect of such deliveries on the solution quality.


Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation

Neural Information Processing Systems

While recent developments in autonomous vehicle (AV) technology highlight substantial progress, we lack tools for rigorous and scalable testing. Real-world testing, the de facto evaluation environment, places the public in danger, and, due to the rare nature of accidents, will require billions of miles in order to statistically validate performance claims. We implement a simulation framework that can test an entire modern autonomous driving system, including, in particular, systems that employ deep-learning perception and control algorithms. Using adaptive importance-sampling methods to accelerate rare-event probability evaluation, we estimate the probability of an accident under a base distribution governing standard traffic behavior. We demonstrate our framework on a highway scenario, accelerating system evaluation by 2-20 times over naive Monte Carlo sampling methods and 10-300P times (where P is the number of processors) over real-world testing.


Tesla Reveals Specs of its New AI-Powered Full Self-Driving Computer

#artificialintelligence

In April, at a special event at Tesla's Palo Alto, California headquarters called Tesla Autonomy Investor Day, Tesla CEO Elon Musk announced that Tesla vehicles are using a new custom-designed processor to power its Autopilot full self-driving (FSD) system. At the time Musk said that no chip was available that had the processing power and power constraints that Tesla required, so the automaker built its own from scratch. Now the technical details of the new chip have been revealed for the first time. At the Hot Chips conference in San Francisco on Tuesday, Tesla's VP of hardware engineering Pete Bannon revealed of the details of the chipset that will power Tesla's future Autopilot, full self-driving (FSD) system. Bannon said that the new AI-powered chip is 21 times faster that the Nvidia chip it's replacing and only 80% of the cost.


India only country with positive trade outlook out of seven big economies: DHL's AI

#artificialintelligence

December 07, 2019: According to the AI-based prediction from'DHL Global Trade Barometer', India is the only country with a positive trade outlook for the running quarter out of the world's seven largest economies. Thanks to the strong maritime exports and Imports that will maintain India's trade growth over the three-month period ending in January 2020. The DHL Global Trade Barometer, an indicator of global trade developments calculated using artificial intelligence and big data, predict mildly positive growth for Indian trade with the country's Index rising five points to 54. The positive outlook is driven primarily by an uptake in ocean imports of basic & industrial raw materials and chemicals & products, coupled with a gradual revival in air exports of consumer fashion goods. In total, ocean trade grew by 10 points, maintaining India's positive outlook even as air trade forecasts experience relative weakness.


Flexible sampling of discrete data correlations without the marginal distributions

Neural Information Processing Systems

Learning the joint dependence of discrete variables is a fundamental problem in machine learning, with many applications including prediction, clustering and dimensionality reduction. More recently, the framework of copula modeling has gained popularity due to its modular parametrization of joint distributions. Among other properties, copulas provide a recipe for combining flexible models for univariate marginal distributions with parametric families suitable for potentially high dimensional dependence structures. More radically, the extended rank likelihood approach of Hoff (2007) bypasses learning marginal models completely when such information is ancillary to the learning task at hand as in, e.g., standard dimensionality reduction problems or copula parameter estimation. The main idea is to represent data by their observable rank statistics, ignoring any other information from the marginals.


Flexible neural representation for physics prediction

Neural Information Processing Systems

Humans have a remarkable capacity to understand the physical dynamics of objects in their environment, flexibly capturing complex structures and interactions at multiple levels of detail. Inspired by this ability, we propose a hierarchical particle-based object representation that covers a wide variety of types of three-dimensional objects, including both arbitrary rigid geometrical shapes and deformable materials. We then describe the Hierarchical Relation Network (HRN), an end-to-end differentiable neural network based on hierarchical graph convolution, that learns to predict physical dynamics in this representation. Compared to other neural network baselines, the HRN accurately handles complex collisions and nonrigid deformations, generating plausible dynamics predictions at long time scales in novel settings, and scaling to large scene configurations. These results demonstrate an architecture with the potential to form the basis of next-generation physics predictors for use in computer vision, robotics, and quantitative cognitive science.


The top AI and machine learning conferences to attend in 2020

#artificialintelligence

While artificial intelligence may be powering Siri, Google searches, and the advance of self-driving cars, many people still have sci-fi-inspired notions of what AI actually looks like and how it will affect our lives. AI-focused conferences give researchers and business executives a clear view of what is already working and what is coming down the road. To bring AI researchers from academia and industry together to share their work, learn from one another, and inspire new ideas and collaborations, there are a plethora of AI-focused conferences around the world. There's a growing number of AI conferences geared toward business leaders who want to learn how to use artificial intelligence and related machine learning and deep learning to propel their companies beyond their competitors. So, whether you're a post-doc, a professor working on robotics, or a programmer for a major company, there are conferences out there to help you code better, network with other researchers, and show off your latest papers.


6 revolutionary things to know about Machine Learning

#artificialintelligence

We are stepping into an avant-garde period, powered by advances in robotics, the adoption of smart home appliances, intelligent retail stores, self-driving car technology etc. Machine leaning is at the forefront of all these new-age technological advancements. The development of automated machines which have the capability match up to or maybe even surpass the human intelligence in the coming time. Machine learning is undoubtedly the next'big' thing. And, it is believed that most of the future technologies will be hooked on to it. Machine learning is given a lot of importance because it helps in prophesying behavior and spotting patterns that humans fail to predict.


Deep Double Descent

#artificialintelligence

We show that the double descent phenomenon occurs in CNNs, ResNets, and transformers: performance first improves, then gets worse, and then improves again with increasing model size, data size, or training time. This effect is often avoided through careful regularization. While this behavior appears to be fairly universal, we don't yet fully understand why it happens, and view further study of this phenomenon as an important research direction. The peak occurs predictably at a "critical regime," where the models are barely able to fit the training set. As we increase the number of parameters in a neural network, the test error initially decreases, increases, and, just as the model is able to fit the train set, undergoes a second descent.


ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization

Neural Information Processing Systems

The adaptive momentum method (AdaMM), which uses past gradients to update descent directions and learning rates simultaneously, has become one of the most popular first-order optimization methods for solving machine learning problems. However, AdaMM is not suited for solving black-box optimization problems, where explicit gradient forms are difficult or infeasible to obtain. In this paper, we propose a zeroth-order AdaMM (ZO-AdaMM) algorithm, that generalizes AdaMM to the gradient-free regime. We show that the convergence rate of ZO-AdaMM for both convex and nonconvex optimization is roughly a factor of $O(\sqrt{d})$ worse than that of the first-order AdaMM algorithm, where $d$ is problem size. In particular, we provide a deep understanding on why Mahalanobis distance matters in convergence of ZO-AdaMM and other AdaMM-type methods.