Machine learning is predicated on the concept of generalization: a model achieving low error on a sufficiently large training set should also perform well on novel samples from the same distribution. We show that both data whitening and second order optimization can harm or entirely prevent generalization. In general, model training harnesses information contained in the sample-sample second moment matrix of a dataset. For a general class of models, namely models with a fully connected first layer, we prove that the information contained in this matrix is the only information which can be used to generalize. Models trained using whitened data, or with certain second order optimization schemes, have less access to this information; in the high dimensional regime they have no access at all, producing models that generalize poorly or not at all. We experimentally verify these predictions for several architectures, and further demonstrate that generalization continues to be harmed even when theoretical requirements are relaxed. However, we also show experimentally that regularized second order optimization can provide a practical tradeoff, where training is still accelerated but less information is lost, and generalization can in some circumstances even improve.

A standard method for testing some of the mechanical properties of materials is to poke them with a sharp point. This "indentation technique" can provide detailed measurements of how the material responds to the point's force, as a function of its penetration depth. With advances in nanotechnology during the past two decades, the indentation force can be measured to a resolution on the order of one-billionth of a Newton (a measure of the force approximately equivalent to the force you feel when you hold a medium-sized apple in your hand), and the sharp tip's penetration depth can be captured to a resolution as small as a nanometer, or about 1/100,000 the diameter of a human hair. Such instrumented nanoindentation tools have provided new opportunities for probing physical properties in a wide variety of materials, including metals and alloys, plastics, ceramics, and semiconductors. But while indentation techniques, including nanoindentation, work well for measuring some properties, they exhibit large errors when probing plastic properties of materials -- the kind of permanent deformation that happens, for example, if you press your thumb into a piece of silly putty and leave a dent, or when you permanently bend a paper clip using your fingers.

Robots in human environments will need to interact with a wide variety of articulated objects such as cabinets, drawers, and dishwashers while assisting humans in performing day-to-day tasks. Existing methods either require objects to be textured or need to know the articulation model category a priori for estimating the model parameters for an articulated object. We propose ScrewNet, a novel approach that estimates an object's articulation model directly from depth images without requiring a priori knowledge of the articulation model category. ScrewNet uses screw theory to unify the representation of different articulation types and perform category-independent articulation model estimation. We evaluate our approach on two benchmarking datasets and compare its performance with a current state-of-the-art method. Results demonstrate that ScrewNet can successfully estimate the articulation models and their parameters for novel objects across articulation model categories with better on average accuracy than the prior state-of-the-art method.

This paper presents a new variable selection approach integrated with Gaussian process (GP) regression. We consider a sparse projection of input variables and a general stationary covariance model that depends on the Euclidean distance between the projected features. The sparse projection matrix is considered as an unknown parameter. We propose a forward stagewise approach with embedded gradient descent steps to co-optimize the parameter with other covariance parameters based on the maximization of a non-convex marginal likelihood function with a concave sparsity penalty, and some convergence properties of the algorithm are provided. The proposed model covers a broader class of stationary covariance functions than the existing automatic relevance determination approaches, and the solution approach is more computationally feasible than the existing MCMC sampling procedures for the automatic relevance parameter estimation with a sparsity prior. The approach is evaluated for a large number of simulated scenarios. The choice of tuning parameters and the accuracy of the parameter estimation are evaluated with the simulation study. In the comparison to some chosen benchmark approaches, the proposed approach has provided a better accuracy in the variable selection. It is applied to an important problem of identifying environmental factors that affect an atmospheric corrosion of metal alloys.

Dynamic dispatching is one of the core problems for operation optimization in traditional industries such as mining, as it is about how to smartly allocate the right resources to the right place at the right time. Conventionally, the industry relies on heuristics or even human intuitions which are often short-sighted and sub-optimal solutions. Leveraging the power of AI and Internet of Things (IoT), data-driven automation is reshaping this area. However, facing its own challenges such as large-scale and heterogenous trucks running in a highly dynamic environment, it can barely adopt methods developed in other domains (e.g., ride-sharing). In this paper, we propose a novel Deep Reinforcement Learning approach to solve the dynamic dispatching problem in mining. We first develop an event-based mining simulator with parameters calibrated in real mines. Then we propose an experience-sharing Deep Q Network with a novel abstract state/action representation to learn memories from heterogeneous agents altogether and realizes learning in a centralized way. We demonstrate that the proposed methods significantly outperform the most widely adopted approaches in the industry by $5.56\%$ in terms of productivity. The proposed approach has great potential in a broader range of industries (e.g., manufacturing, logistics) which have a large-scale of heterogenous equipment working in a highly dynamic environment, as a general framework for dynamic resource allocation.

3D object detection is a core perceptual challenge for robotics and autonomous driving. However, the class-taxonomies in modern autonomous driving datasets are significantly smaller than many influential 2D detection datasets. In this work, we address the long-tail problem by leveraging both the large class-taxonomies of modern 2D datasets and the robustness of state-of-the-art 2D detection methods. We proceed to mine a large, unlabeled dataset of images and LiDAR, and estimate 3D object bounding cuboids, seeded from an off-the-shelf 2D instance segmentation model. Critically, we constrain this ill-posed 2D-to-3D mapping by using high-definition maps and object size priors. The result of the mining process is 3D cuboids with varying confidence. This mining process is itself a 3D object detector, although not especially accurate when evaluated as such. However, we then train a 3D object detection model on these cuboids, consistent with other recent observations in the deep learning literature, we find that the resulting model is fairly robust to the noisy supervision that our mining process provides. We mine a collection of 1151 unlabeled, multimodal driving logs from an autonomous vehicle and use the discovered objects to train a LiDAR-based object detector. We show that detector performance increases as we mine more unlabeled data. With our full, unlabeled dataset, our method performs competitively with fully supervised methods, even exceeding the performance for certain object categories, without any human 3D annotations.

Worldwide, more than 2,200 cement plants consume enormous amounts of fuel and electric energy--and produce approximately 5 percent of all global CO₂ emissions. Cement plant owners are under intensifying pressure to curb emissions and benefit from more efficient and profitable plants. Still, they have a long way to go. Significant fluctuations and performance volatility in throughput, energy usage, and other operating parameters of up to 50 percent from average or more remain. Such situations persist largely because conventional automation and control systems have reached their limits for handling inherently unstable chemical process–type operations.

The ease with which you shop at Amazon and scroll though different products that are customised specific to your taste is the result of AI technology that analyses and predicts your shopping behavior. There are countless AI start-ups who are founded for the primary reason of using AI to make the world a better place. The challenges that the world faces today – primarily climate change – is a huge motivator for AI innovation. Every AI idea is bound to help us face such challenges. In 2018, venture funding for AI grew to about 9.3 billion dollars in U.S. alone.

We propose a data-driven method to extract dissimilarity between materials, with respect to a given target physical property. The technique is based on an ensemble method with Kernel ridge regression as the predicting model; multiple random subset sampling of the materials is done to generate prediction models and the corresponding contributions of the reference training materials in detail. The distribution of the predicted values for each material can be approximated by a Gaussian mixture model. The reference training materials contributed to the prediction model that accurately predicts the physical property value of a specific material, are considered to be similar to that material, or vice versa. Evaluations using synthesized data demonstrate that the proposed method can effectively measure the dissimilarity between data instances. An application of the analysis method on the data of Curie temperature (TC) of binary 3d transition metal 4f rare earth binary alloys also reveals meaningful results on the relations between the materials. The proposed method can be considered as a potential tool for obtaining a deeper understanding of the structure of data, with respect to a target property, in particular.

A tiny robotic beetle that can crawl, climb slopes, carry different loads and has'muscles' powered by a liquid methanol fuel has been developed by researchers. Roboticists from California developed the bug-sized'RoBeetle' -- which weighs in at less than 1/100th of an ounce -- to explore new means of propelling tiny machines. It is hoped that the design will inspire a new breed of small-scale robots that can perform simple tasks without the need for external controls or bulky components. A tiny robotic beetle that can crawl, climb slopes, carry different loads and has'muscles' powered by a liquid methanol fuel has been developed by researchers. When building robots of the scale of the RoBeetle, batteries become relatively inefficient at storing energy, especially when compared to the amount that can be stored in animal fat -- the biological equivalent of a fuel tank.