Space exploration missions have seen use of increasingly sophisticated robotic systems with ever more autonomy. Deep learning promises to take this even a step further, and has applications for high - level tasks, like path planning, as well as low - level tasks, like motion control, which are critical components for mission efficiency and success. Using deep reinforcement end - to - end learning with randomized reward function parameters during training, we teach a simulated 8 degree - of - freedom quadruped ant - like robot to travel anywhere within a perimeter, conducting path plan and motion control on a single neural network, without any system model or prior knowledge of the terrain or environment. Our approach also allows for user specified waypoints, which could translate well to either fully autonomous or semi - autonomous/tele - operated space applications that encounter delay times. We train ed the agent using randomly ge nerated waypoints linked to the reward function and passed waypoint coordinates as inputs to the neural network. Such applications show promise on a variety of space exploration robots, including high speed rovers for fast locomotion and legged cave robots for rough terrain.

Although over 100 languages are supported by strong off-the-shelf machine translation systems, only a subset of them possess large annotated corpora for named entity recognition. Motivated by this fact, we leverage machine translation to improve annotation-projection approaches to cross-lingual named entity recognition. We propose a system that improves over prior entity-projection methods by: (a) leveraging machine translation systems twice: first for translating sentences and subsequently for translating entities; (b) matching entities based on orthographic and phonetic similarity; and (c) identifying matches based on distributional statistics derived from the dataset. Our approach improves upon current state-of-the-art methods for cross-lingual named entity recognition on 5 diverse languages by an average of 4.1 points. Further, our method achieves state-of-the-art F_1 scores for Armenian, outperforming even a monolingual model trained on Armenian source data.

In order to build a national injury surveillance system based on emergency room (ER) visits we are developing a coding system to classify their causes from clinical notes content. Supervised learning techniques have shown good results in this area but require to manually build a large learning annotated dataset. New levels of performance have been recently achieved in neural language models (NLM) with the use of models based on the Transformer architecture with an unsupervised generative pre-training step. Our hypothesis is that methods involving a generative self-supervised pre-training step significantly reduce the number of annotated samples required for supervised fine-tuning. In this case study, we assessed whether we could predict from free text clinical notes whether a visit was the consequence of a traumatic or a non-traumatic event. We compared two strategies: Strategy A consisted in training the GPT-2 NLM on the full 161 930 samples dataset with all labels (trauma/non-trauma). In Strategy B, we split the training dataset in two parts, a large one of 151 930 samples without any label for the self-supervised pre-training phase and a smaller one (up to 10 000 samples) for the supervised fine-tuning with labels. While strategy A needed to process 40 000 samples to achieve good performance (AUC>0.95), strategy B needed only 500 samples, a gain of 80. Moreover, an AUC of 0.93 was measured with only 30 labeled samples processed 3 times (3 epochs). To conclude, it is possible to adapt a multi-purpose NLM model such as the GPT-2 to create a powerful tool for classification of free-text notes with the need of a very small number of labeled samples. Only two modalities (trauma/non-trauma) were predicted for this case study but the same method can be applied for multimodal classification tasks such as diagnosis/disease terminologies.

Client requirements are mostly too specific to a niche domain. Hence the availability of a huge high-quality dataset is not available. Client-based companies are usually working on multiple projects even under the same client. Their resources are much more distributed across different tasks and even expertise. Depending upon the client for data, especially for POCs / POVs/MVPs, is a lost cause.

Nvidia Research has been making strides in using deep learning to train models for various tasks. Recently, the company clocked the fastest training times for BERT and trained the largest ever transformer-based model. However, as expected, algorithms based on deep learning require a large dataset to begin with, and that is a luxury in many situations. Along with continuing research using deep learning, the company focused its efforts in another direction as well. And the firm, at its Seattle Robotics Lab, developed a novel algorithm, called 6-DoF GraspNet, that allows robots to grasp arbitrary objects.

Recent years have seen a rising interest in developing AI algorithms for real world big data domains ranging from autonomous cars to personalized assistants. At the core of these algorithms are architectures that combine deep neural networks, for approximating the underlying multidimensional state-spaces, with reinforcement learning, for controlling agents that learn to operate in said state-spaces towards achieving a given objective. The talk will first outline notable past and future efforts in deep reinforcement learning as well as identify fundamental problems that this technology has been struggling to overcome. Towards mitigating these problems (and open up an alternative path to general artificial intelligence), I will then summarize a brain computing model of intelligence, rooted in the latest findings in neuroscience. The talk will conclude with an overview of the recent research efforts in the field of multi-agent systems, to provide the future teams of humans and agents with the necessary tools that allow them to safely co-exist.

We invite you to join Intel's Next Generation & Standards (NGS) Group and the 5G revolution! We are a global team of passionate engineers and technologists from diverse industry backgrounds, working together to realize a world of connected computing. Intel's NGS team is chartered with developing advanced prototypes of various technologies to deliver innovative and state of the art wireless experiences into the market within the Internet of Things, 5G Next Generation Wearable and IoT solutions and other world-class wireless connectivity technologies and products. The Next Generation and Standards Group's mission is to lead standards, ecosystem, and prototyping development efforts across Intel for advanced wireless communications IP, starting with 5G and beyond. This group brings together a panorama of competencies including standards creation, ecosystem development, use case and business development in creating advanced prototypes and technologies that propel Intel's leadership.

Deep Networks have been shown to provide state-of-the-art performance in many machine learning challenges. Unfortunately, they are susceptible to various types of noise, including adversarial attacks and corrupted inputs. In this work we introduce a formal definition of robustness which can be viewed as a localized Lipschitz constant of the network function, quantified in the domain of the data to be classified. We compare this notion of robustness to existing ones, and study its connections with methods in the literature. We evaluate this metric by performing experiments on various competitive vision datasets.

The Ghent Altarpiece, which researchers have analyzed using a combination of X-ray imaging and machine learning. AI is the future, and it's also the past. Not just in the sense of having been developed in previous years and decades, but also in the sense of being capable of recreating human history. This power was highlighted vividly by a study published at the end of August by researchers from University College London and Duke University, who managed to use artificial intelligence to create separate representations of two images that had been painted on both sides of a single panel. More specifically, they used X-ray imaging techniques to produce a combined representation of the outer panels of the famous 15th Century Ghent Altarpiece painting.

This blog, intended for developers with professional level understanding of Deep Learning, will help you produce a production ready AI text-to-speech model. Converting text into high quality, natural sounding speech in real-time has been a challenging task for decades. State-of-the-art speech synthesis models are based on parametric neural networks1. Text-to-speech (TTS) synthesis is typically done in two steps. The optimized Tacotron2 model2 and the new WaveGlow model1 take advantage of Tensor Cores on NVIDIA Volta and Turing GPUs to convert text into high quality natural sounding speech in real-time.