This paper investigates the anti-jamming performance of a cognitive radar under a partially observable Markov decision process (POMDP) model. First, we obtain an explicit expression for uncertainty of jammer dynamics, which paves the way for illuminating the performance metric of probability of being jammed for the radar beyond a conventional signal-to-noise ratio ($\mathsf{SNR}$) based analysis. Considering two frequency hopping strategies developed in the framework of reinforcement learning (RL), this performance metric is analyzed with deep Q-network (DQN) and long short term memory (LSTM) networks under various uncertainty values. Finally, the requirement of the target network in the RL algorithm for both network architectures is replaced with a softmax operator. Simulation results show that this operator improves upon the performance of the traditional target network.

Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized to be non-transparent and their predictions not traceable by humans. Furthermore, the models learn from artificial datasets, often with bias or contaminated discriminating content. Through their increased distribution, decision-making algorithms can contribute promoting prejudge and unfairness which is not easy to notice due to lack of transparency. Hence, scientists developed several so-called explanators or explainers which try to point out the connection between input and output to represent in a simplified way the inner structure of machine learning black boxes. In this survey we differ the mechanisms and properties of explaining systems for Deep Neural Networks for Computer Vision tasks. We give a comprehensive overview about taxonomy of related studies and compare several survey papers that deal with explainability in general. We work out the drawbacks and gaps and summarize further research ideas.

Automated reasoning and theorem proving have recently become major challenges for machine learning. In other domains, representations that are able to abstract over unimportant transformations, such as abstraction over translations and rotations in vision, are becoming more common. Standard methods of embedding mathematical formulas for learning theorem proving are however yet unable to handle many important transformations. In particular, embedding previously unseen labels, that often arise in definitional encodings and in Skolemization, has been very weak so far. Similar problems appear when transferring knowledge between known symbols. We propose a novel encoding of formulas that extends existing graph neural network models. This encoding represents symbols only by nodes in the graph, without giving the network any knowledge of the original labels. We provide additional links between such nodes that allow the network to recover the meaning and therefore correctly embed such nodes irrespective of the given labels. We test the proposed encoding in an automated theorem prover based on the tableaux connection calculus, and show that it improves on the best characterizations used so far. The encoding is further evaluated on the premise selection task and a newly introduced symbol guessing task, and shown to correctly predict 65% of the symbol names.

In densely populated environments, socially compliant navigation is critical for autonomous robots as driving close to people is unavoidable. This manner of social navigation is challenging given the constraints of human comfort and social rules. Traditional methods based on hand-craft cost functions to achieve this task have difficulties to operate in the complex real world. Other learning-based approaches fail to address the naturalness aspect from the perspective of collective formation behaviors. We present an autonomous navigation system capable of operating in dense crowds and utilizing information of social groups. The underlying system incorporates a deep neural network to track social groups and join the flow of a social group in facilitating the navigation. A collision avoidance layer in the system further ensures navigation safety. In experiments, our method generates socially compliant behaviors as state-of-the-art methods. More importantly, the system is capable of navigating safely in a densely populated area (10+ people in a 10m x 20m area) following crowd flows to reach the goal.

The leading approaches in language modeling are all obsessed with TV shows of my youth - namely Transformers and Sesame Street. Transformers this, Transformers that, and over here a bonfire worth of GPU-TPU-neuromorphic wafer scale silicon. We opt for the lazy path of old and proven techniques with a fancy crypto inspired acronym: the Single Headed Attention RNN (SHA-RNN). The author's lone goal is to show that the entire field might have evolved a different direction if we had instead been obsessed with a slightly different acronym and slightly different result. We take a previously strong language model based only on boring LSTMs and get it to within a stone's throw of a stone's throw of state-of-the-art byte level language model results on enwik8. This work has undergone no intensive hyperparameter optimization and lived entirely on a commodity desktop machine that made the author's small studio apartment far too warm in the midst of a San Franciscan summer. The final results are achievable in plus or minus 24 hours on a single GPU as the author is impatient. The attention mechanism is also readily extended to large contexts with minimal computation. Take that Sesame Street.

In recent years, person re-identification (PReID) has become a hot topic in computer vision duo to it is an important part in intelligent surveillance. Many state-of-the-art PReID methods are attention-based or multi-scale feature learning deep models. However, introducing attention mechanism may lead to some important feature information losing issue. Besides, most of the multi-scale models embedding the multi-scale feature learning block into the feature extraction deep network, which reduces the efficiency of inference network. To address these issue, in this study, we introduce an attention deep architecture with multi-scale deep supervision for PReID. Technically, we contribute a reverse attention block to complement the attention block, and a novel multi-scale layer with deep supervision operator for training the backbone network. The proposed block and operator are only used for training, and discard in test phase. Experiments have been performed on Market-1501, DukeMTMC-reID and CUHK03 datasets. All the experiment results show that the proposed model significantly outperforms the other competitive state-of-the-art methods.

We decided to run the ML Study Group for students who were at python study group in order to walk with them all the way right to learn the best practices on Machine Learning on Cloud and with TensorFlow. Machine Learning Study Group is a series of sessions where we learn together the fundamentals of ML and Deep Learning on GCP, using APIs and TensorFlow as well as learn more about models and how to build your own model in python. This Study Jam is intended for those who wish to learn about ML from a practical, applied perspective that will enable you to use machine learning in your everyday projects and learn about the power of TensorFlow. Main topics: 1- ML APIs on GCP 2- Algorithms 3- Sklearn and Keras 4- neural network 5- TensorFlow we will go through:- GCP, algorithms, ML using python, sklearn, keras, computer vision (CNN), speech recognition, TensorFlow, neural network and more.

To view the code, training visualizations, and more information about the python example at the end of this post, visit the Comet project page. While much of the writing and literature on deep learning concerns computer vision and natural language processing (NLP), audio analysis -- a field that includes automatic speech recognition (ASR), digital signal processing, and music classification, tagging, and generation -- is a growing subdomain of deep learning applications. Some of the most popular and widespread machine learning systems, virtual assistants Alexa, Siri and Google Home, are largely products built atop models that can extract information from audio signals. Many of our users at Comet are working on audio related machine learning tasks such as audio classification, speech recognition and speech synthesis, so we built them tools to analyze, explore and understand audio data using Comet's meta machine-learning platform. This post is focused on showing how data scientists and AI practitioners can use Comet to apply machine learning and deep learning methods in the domain of audio analysis.

Whether it's monitoring vehicles for lane drift, recognizing human faces or voices to unlock a phone, or recommending e-commerce products or streaming movies -- most people know that AI is watching and interacting with us more than ever before. What is not so well-known is how much AI has also established itself as a crucial tool in academics, particularly for scientific discovery. An interdisciplinary team of chemists, physicists, and computer scientists from the University of Warwick, the Technical University of Berlin, and the University of Luxembourg have developed a deep learning algorithm that leverages fundamental quantum mechanics equations to accurately predict the quantum mechanical wave functions of molecules. This provides a probability distribution for the value of each observable of the quantum system, from which additional ground-truth properties of the molecules can be derived. The research team say the study "opens promising avenues to perform inverse design of molecular structures for targeting electronic property optimization and a clear path towards increased synergy of machine learning and quantum chemistry," The team was assembled through a UCLA fellowship program on machine learning in quantum physics and has been working together for three years.

At the 2019 Supercomputing Conference in Denver, Colorado, global supercomputer leader Cray, a Hewlett Packard Enterprise company, announced that the King Abdullah University of Science and Technology (KAUST) in Saudi Arabia has selected a Cray CS-Storm 500NX supercomputer to support innovation in the university and the nation through a strategic artificial intelligence (AI) initiative. The added power of the GPU-accelerated CS-Storm system provides KAUST researchers greater computational capabilities to drive positive and significant outcomes in the university's core research areas of global significance: food, water, energy, the environment, and digitalization. From helping to build smart cities to developing AI algorithms that think like scientists, KAUST is the largest research center in the Middle East that brings together faculty, researchers and graduate students to leverage the interconnectedness of science and engineering. With an 8:2 ratio of GPUs to CPUs, the new Cray CS-Storm 500NX supercomputer will meet KAUST's most demanding computing requirements for production scalability, while also delivering a low total cost of ownership. Engineered for the convergence of modeling, simulation and analytics, the CS-Storm fast-started KAUST's AI journey and provides researchers and scientists the highly-advanced supercomputing and software capabilities required to analyze large volumes of data for rapid insight, where simulation alone is unsatisfactory for predicting real-world outcomes.