Sponsored Artificial intelligence (AI) promises to revolutionize healthcare. The underlying combination of Machine Learning and analytics can process medical data sets so large and medical images so numerous that they are beyond the scale of researchers, physicians and staff. In so doing, this AI duo promises to help identify patients at risk and prevent the onset of diseases and medical conditions. For existing patients, the hope is AI can identify hidden illnesses, pinpoint medical problems and in the development and application of treatments that assist patient recovery. Yet adoption has been held back thanks to the cost and complexity of building and owning the kinds of high-performance systems needed.

Artificial intelligence has mastered even extremely complex games like chess and Go. However, these games have pre-defined rules and very specific methods of interaction that don't lend themselves to creative choices. A role-playing game like Dungeons and Dragons (DnD) has infinitely more ways to play than a game of chess does, but this hasn't stopped researchers from trying to develop AI systems capable of improvising storylines for DnD or similar tabletop role-playing games. AI researchers are constantly working on new ways to improve the generative language abilities of AI. One of the biggest advances in the past couple of years is the development GPT-2, which was able to generate coherent stories on the fly.

Artificial intelligence has mastered even extremely complex games like chess and Go. However, these games have pre-defined rules and very specific methods of interaction that don't lend themselves to creative choices. A role-playing game like Dungeons and Dragons (DnD) has infinitely more ways to play than a game of chess does, but this hasn't stopped researchers from trying to develop AI systems capable of improvising storylines for DnD or similar tabletop role-playing games. AI researchers are constantly working on new ways to improve the generative language abilities of AI. One of the biggest advances in the past couple of years is the development GPT-2, which was able to generate coherent stories on the fly.

Equipped with best-in-class AI solutions, Samsung Exynos processors enable users to enjoy the next-generation mobile experiences. Launched in 2018, Exynos 9810 was the first processor in the series with deep learning software. With the addition of neural processing unit integration, the Exynos series delivers unmatched performance for mobile AI operations. The newly introduced Exynos 990 processor, featuring dual-core neural processing unit (NPU) and improved digital signal processor (DSP), makes on-device AI practical through faster AI processing capabilities up to approx. By developing algorithms that are four times lighter and eight times faster than existing solutions, Samsung Exynos will continuously set a new standard for AI processing to push the boundaries of the next generation mobile experience.

Computer scientists from Rice, supported by collaborators from Intel, will present their results today at the Austin Convention Center as a part of the machine learning systems conference MLSys. Many companies are investing heavily in GPUs and other specialized hardware to implement deep learning, a powerful form of artificial intelligence that's behind digital assistants like Alexa and Siri, facial recognition, product recommendation systems and other technologies. For example, Nvidia, the maker of the industry's gold-standard Tesla V100 Tensor Core GPUs, recently reported a 41% increase in its fourth quarter revenues compared with the previous year. Rice researchers created a cost-saving alternative to GPU, an algorithm called "sub-linear deep learning engine" (SLIDE) that uses general purpose central processing units (CPUs) without specialized acceleration hardware. "Our tests show that SLIDE is the first smart algorithmic implementation of deep learning on CPU that can outperform GPU hardware acceleration on industry-scale recommendation datasets with large fully connected architectures," said Anshumali Shrivastava, an assistant professor in Rice's Brown School of Engineering who invented SLIDE with graduate students Beidi Chen and Tharun Medini.

A stable version of an automation tool released this week aims to make life easier machine learning developers training and scaling models, then deploying ML workloads atop Kubernetes clusters. Roughly two years after its open source release, Kubeflow 1.0 leverages the de facto standard cluster orchestrator to aid data scientists and ML developers in tapping cloud resources to run those workloads in production. Among the stable workflow applications released on Monday (March 2) are a central dashboard, Jupyter notebook controller and web application along with TensorFlow and PyTorch operators for distributed training. Contributors from Google, IBM, Cisco Systems, Microsoft and data management specialist Arrikto said Jupyter notebooks can be used to streamline model development. Other tools can then be used to build application containers and leverage Kubernetes resources to train models.

Approximate inference in probability models is a fundamental task in machine learning. Approximate inference provides powerful tools to Bayesian reasoning, decision making, and Bayesian deep learning. The main goal is to estimate the expectation of interested functions w.r.t. a target distribution. When it comes to high dimensional probability models and large datasets, efficient approximate inference becomes critically important. In this thesis, we propose a new framework for approximate inference, which combines the advantages of these three frameworks and overcomes their limitations. Our proposed four algorithms are motivated by the recent computational progress of Stein's method. Our proposed algorithms are applied to continuous and discrete distributions under the setting when the gradient information of the target distribution is available or unavailable. Theoretical analysis is provided to prove the convergence of our proposed algorithms. Our adaptive IS algorithm iteratively improves the importance proposal by functionally decreasing the KL divergence between the updated proposal and the target. When the gradient of the target is unavailable, our proposed sampling algorithm leverages the gradient of a surrogate model and corrects induced bias with importance weights, which significantly outperforms other gradient-free sampling algorithms. In addition, our theoretical results enable us to perform the goodness-of-fit test on discrete distributions. At the end of the thesis, we propose an importance-weighted method to efficiently aggregate local models in distributed learning with one-shot communication. Results on simulated and real datasets indicate the statistical efficiency and wide applicability of our algorithm.

There has been a surge of interest in continual learning and federated learning, both of which are important in training deep neural networks in real-world scenarios. Yet little research has been done regarding the scenario where each client learns on a sequence of tasks from private local data. This problem of federated continual learning poses new challenges to continual learning, such as utilizing knowledge and preventing interference from tasks learned on other clients. To resolve these issues, we propose a novel federated continual learning framework, Federated continual learning with Adaptive Parameter Communication, which additively decomposes the network weights into global shared parameters and sparse task-specific parameters. This decomposition allows to minimize interference between incompatible tasks, and also allows inter-client knowledge transfer by communicating the sparse task-specific parameters. Our federated continual learning framework is also communication-efficient, due to high sparsity of the parameters and sparse parameter update. We validate APC against existing federated learning and local continual learning methods under varying degrees of task similarity across clients, and show that our model significantly outperforms them with a large reduction in the communication cost.

Precise trajectory prediction of surrounding vehicles is critical for decision-making of autonomous vehicles and learning-based approaches are well recognized for the robustness. However, state-of-the-art learning-based methods ignore 1) the feasibility of the vehicle's multi-modal state information for prediction and 2) the mutual exclusive relationship between the global traffic scene receptive fields and the local position resolution when modeling vehicles' interactions, which may influence prediction accuracy. Therefore, we propose a vehicle-descriptor based LSTM model with the dilated convolutional social pooling (VD+DCS-LSTM) to cope with the above issues. First, each vehicle's multi-modal state information is employed as our model's input and a new vehicle descriptor encoded by stacked sparse auto-encoders is proposed to reflect the deep interactive relationships between various states, achieving the optimal feature extraction and effective use of multi-modal inputs. Secondly, the LSTM encoder is used to encode the historical sequences composed of the vehicle descriptor and a novel dilated convolutional social pooling is proposed to improve modeling vehicles' spatial interactions. Thirdly, the LSTM decoder is used to predict the probability distribution of future trajectories based on maneuvers. The validity of the overall model was verified over the NGSIM US-101 and I-80 datasets and our method outperforms the latest benchmark.

Organize songs, albums, and artists in groups with shared similarity could be done with the help of genre labels. In this paper, we present a novel approach for automatic classifying musical genre in Brazilian music using only the song lyrics. This kind of classification remains a challenge in the field of Natural Language Processing. We construct a dataset of 138,368 Brazilian song lyrics distributed in 14 genres. We apply SVM, Random Forest and a Bidirectional Long Short-Term Memory (BLSTM) network combined with different word embeddings techniques to address this classification task. Our experiments show that the BLSTM method outperforms the other models with an F1-score average of $0.48$. Some genres like "gospel", "funk-carioca" and "sertanejo", which obtained 0.89, 0.70 and 0.69 of F1-score, respectively, can be defined as the most distinct and easy to classify in the Brazilian musical genres context.