AI, along with machine learning, has the potential to anticipate data to refine processes and to track incongruities all along the supply chain from source to finished product. FREMONT, CA: The potential of Artificial Intelligence (AI) is far beyond human capacity when it comes to things like miniaturization and precision measurements, and also they deliver superior quality assurance. So, what are the advantages one can expect to see as the manufacturing business moves forward into the world of robots and AI? Most businesses are viewing the introduction of AI into the industry with concern, as it needs huge capital investment. Return on investment, on the other hand, is essential and increases as time passes by.

TOKYO/SAN, FRANCISCO – Tesla Inc.'s stock surged 20 percent on Monday in its largest one-day gain since 2013, fueled by a quarterly profit at Panasonic's battery business with the U.S. carmaker and an investor report predicting its shares would rise more than ten-fold by 2024. Shares of Tesla have rallied by over 30 percent since the car maker run by Chief Executive Elon Musk posted its second consecutive quarterly profit last Wednesday, which was viewed as a milestone for the company competing against established heavyweights including General Motors Co. and BMW. The stock is up over 300 percent since early June, helped by Tesla's better-than-expected financial results and ramped up production at its new car factory in Shanghai. Monday's rise came after Panasonic Corp. reported the first quarterly profit in its U.S. battery business with Tesla, which followed years of production troubles and delays. "We are catching up as Tesla is quickly expanding production," Panasonic Chief Financial Officer Hirokazu Umeda told an earnings briefing, referring to battery cell production. "Higher production volume is helping to push down materials costs and erase losses."

Democrats say they'll keep investigating Trump; reaction and analysis on'The Five.' The hosts of "The Five" dismissed Sunday's claim by Rep. Adam Schiff, D-Calif., that Democrats "proved" their case against the president in the Senate impeachment trial and he would not have done anything differently. "Look, there's nothing that I can see that we could have done differently, because as the senators have already admitted, we've proved our case," Schiff said on CBS News' "Face The Nation." "[Schiff] has to say that, but I'm sure he regrets it," co-host Jesse Watters said. "I mean, if they had done it properly and not started it out in a secret basement with no lawyers present, maybe they would have gone differently. Maybe they would have build a stronger case. Maybe they would have gone to a judge to compel witness testimony and maybe delivered. "They could have argued in a more convincing fashion, but they wanted to do a rush job to fit a political calendar," Watters added. "They didn't really care about making a really strong constitutional case so they can continue to investigate the president." Co-host Dana Perino called Trump's eventual acquittal a "loss" for Democrats and said it only emboldens the president. "Acquittal is a loss," Perino said. "And then whoever wins in a fight like this gets to write the history." "President Trump is like... 'Pac-Man,'" Perino said, comparing him to the popular video game character from the 1980s. "You go along, ding, ding, ding, and then you eat the fruit and you get bigger and stronger and you get another man, like, that's President Trump." Co-host Greg Gutfeld predicted that Democrats will keep the proceedings "running," with congressional investigations becoming "as mundane as living next to an airport "You know, we used to think planes were interesting," he said.

A multi-objective prediction method of multi-stage pump method based on neural network with data augmentation is proposed. In order to study the highly nonlinear relationship between key design variables and centrifugal pump external characteristic values (head and power), the neural network model (NN) is built in comparison with the quadratic response surface model (RSF), the radial basis Gaussian response surface model (RBF), and the Kriging model (KRG). The numerical model validation experiment of another type of single stage centrifugal pump showed that numerical model based on CFD is quite accurate and fair. All of prediction models are trained by 60 samples under the different combination of three key variables in design range respectively. The accuracy of the head and power based on the four predictions models are analyzed comparing with the CFD simulation values. The results show that the neural network model has better performance in all external characteristic values comparing with other three surrogate models. Finally, a neural network model based on data augmentation (NNDA) is proposed for the reason that simulation cost is too high and data is scarce in mechanical simulation field especially in CFD problems. The model with data augmentation can triple the data by interpolation at each sample point of different attributes. It shows that the performance of neural network model with data augmentation is better than former neural network model. Therefore, the prediction ability of NN is enhanced without more simulation costs. With data augmentation it can be a better prediction model used in solving the optimization problems of multistage pump for next optimization and generalized to finite element analysis optimization problems in future.

This paper presents a reinforcement learning approach to synthesizing task-driven control policies for robotic systems equipped with rich sensory modalities (e.g., vision or depth). Standard reinforcement learning algorithms typically produce policies that tightly couple control actions to the entirety of the system's state and rich sensor observations. As a consequence, the resulting policies can often be sensitive to changes in task-irrelevant portions of the state or observations (e.g., changing background colors). In contrast, the approach we present here learns to create a task-driven representation that is used to compute control actions. Formally, this is achieved by deriving a policy gradient-style algorithm that creates an information bottleneck between the states and the task-driven representation; this constrains actions to only depend on task-relevant information. We demonstrate our approach in a thorough set of simulation results on multiple examples including a grasping task that utilizes depth images and a ball-catching task that utilizes RGB images. Comparisons with a standard policy gradient approach demonstrate that the task-driven policies produced by our algorithm are often significantly more robust to sensor noise and task-irrelevant changes in the environment.

This paper establishes a precise high-dimensional asymptotic theory for Boosting on separable data, taking statistical and computational perspectives. We consider the setting where the number of features (weak learners) p scales with the sample size n, in an over-parametrized regime. On the statistical front, we provide an exact analysis of the generalization error of Boosting, when the algorithm interpolates the training data and maximizes an empirical L1 margin. The angle between the Boosting solution and the ground truth is characterized explicitly. On the computational front, we provide a sharp analysis of the stopping time when Boosting approximately maximizes the empirical L1 margin. Furthermore, we discover that, the larger the margin, the smaller the proportion of active features (with zero initialization). At the heart of our theory lies a detailed study of the maximum L1 margin, using tools from convex geometry. The maximum L1 margin can be precisely described by a new system of non-linear equations, which we study using a novel uniform deviation argument. Preliminary numerical results are presented to demonstrate the accuracy of our theory.

In conventional supervised learning, a training dataset is given with ground-truth labels from a known label set, and the learned model will classify unseen instances to the known labels. In this paper, we study a new problem setting in which there are unknown classes in the training dataset misperceived as other labels, and thus their existence appears unknown from the given supervision. We attribute the unknown unknowns to the fact that the training dataset is badly advised by the incompletely perceived label space due to the insufficient feature information. To this end, we propose the exploratory machine learning, which examines and investigates the training dataset by actively augmenting the feature space to discover potentially unknown labels. Our approach consists of three ingredients including rejection model, feature acquisition, and model cascade. The effectiveness is validated on both synthetic and real datasets.

Agents trained in simulation may make errors when performing actions in the real world due to mismatches between training and execution environments. These mistakes can be dangerous and difficult for the agent to discover because the agent is unable to predict them a priori. In this work, we propose the use of oracle feedback to learn a predictive model of these blind spots in order to reduce costly errors in real-world applications. We focus on blind spots in reinforcement learning (RL) that occur due to incomplete state representation: when the agent lacks necessary features to represent the true state of the world, and thus cannot distinguish between numerous states. We formalize the problem of discovering blind spots in RL as a noisy supervised learning problem with class imbalance. Our system learns models for predicting blind spots within unseen regions of the state space by combining techniques for label aggregation, calibration, and supervised learning. These models take into consideration noise emerging from different forms of oracle feedback, including demonstrations and corrections. We evaluate our approach across two domains and demonstrate that it achieves higher predictive performance than baseline methods, and also that the learned model can be used to selectively query an oracle at execution time to prevent errors. We also empirically analyze the biases of various feedback types and how these biases influence the discovery of blind spots. Further, we include analyses of our approach that incorporate relaxed initial optimality assumptions. (Interestingly, relaxing the assumptions of an optimal oracle and an optimal simulator policy helped our models to perform better.) We also propose extensions to our method that are intended to improve performance when using corrections and demonstrations data.

We present an approach to designing neural network based models that will explicitly satisfy known linear constraints. To achieve this, the target function is modelled as a linear transformation of an underlying function. This transformation is chosen such that any prediction of the target function is guaranteed to satisfy the constraints and can be determined from known physics or, more generally, by following a constructive procedure that was previously presented for Gaussian processes. The approach is demonstrated on simulated and real-data examples.

We present a self-supervised deep multi-task learning framework for electrocardiogram (ECG) -based emotion recognition. The proposed framework consists of two stages of learning a) learning ECG representations and b) learning to classify emotions. ECG representations are learned by a signal transformation recognition network. The network learns high-level abstract representations from unlabeled ECG data. Six different signal transformations are applied to the ECG signals, and transformation recognition is performed as pretext tasks. Training the model on pretext tasks helps our network learn spatiotemporal representations that generalize well across different datasets and different emotion categories. We transfer the weights of the self-supervised network to an emotion recognition network, where the convolutional layers are kept frozen and the dense layers are trained with labelled ECG data. We show that our proposed method considerably improves the performance compared to a network trained using fully-supervised learning. New state-of-the-art results are set in classification of arousal, valence, affective states, and stress for the four utilized datasets. Extensive experiments are performed, providing interesting insights into the impact of using a multi-task self-supervised structure instead of a single-task model, as well as the optimum level of difficulty required for the pretext self-supervised tasks.