Predicting pedestrian movement is critical for human behavior analysis and also for safe and efficient human-agent interactions. However, despite significant advancements, it is still challenging for existing approaches to capture the uncertainty and multimodality of human navigation decision making. In this paper, we propose SocialVAE, a novel approach for human trajectory prediction. The core of SocialVAE is a timewise variational autoencoder architecture that exploits stochastic recurrent neural networks to perform prediction, combined with a social attention mechanism and a backward posterior approximation to allow for better extraction of pedestrian navigation strategies. We show that SocialVAE improves current state-of-the-art performance on several pedestrian trajectory prediction benchmarks, including the ETH/UCY benchmark, Stanford Drone Dataset, and SportVU NBA movement dataset.

Advancements in Telemedicine as an approach to healthcare delivery have heralded a new dawn in modern Medicine. Its fast-paced development in our contemporary society is credence to the advances in Artificial Intelligence and Information Technology. This paper carries out a descriptive study to broadly explore AI's implementations in healthcare delivery with a more holistic view of the usability of various Telemedical Innovations in enhancing Virtual Diagnostic Solutions (VDS). This research further explores notable developments in Deep Learning model optimizations for Virtual Diagnostic Solutions. A further research review on the prospects of Virtual Diagnostic Solutions (VDS) and foreseeable challenges was also highlighted. Conclusively, this research gives a general overview of Artificial Intelligence in Telemedicine with a central focus on Deep Learning-based approaches to Virtual Diagnostic Solutions. NTRODUCTION Healthcare and Medicine are areas of modern society which has gained quite an outstanding level of research attention given current antecedents of virus outbreaks and spikes in anomalies regarding human health. Over the years, advancement in Artificial Intelligence and its resonating research areas such as Telecommunication and information technology has stirred up questions and advanced solutions regarding Human health.

Generative adversarial network (GAN) is a framework for generating fake data using a set of real examples. However, GAN is unstable in the training stage. In order to stabilize GANs, the noise injection has been used to enlarge the overlap of the real and fake distributions at the cost of increasing variance. The diffusion (or smoothing) may reduce the intrinsic underlying dimensionality of data but it suppresses the capability of GANs to learn high-frequency information in the training procedure. Based on these observations, we propose a data representation for the GAN training, called noisy scale-space (NSS), that recursively applies the smoothing with a balanced noise to data in order to replace the high-frequency information by random data, leading to a coarse-to-fine training of GANs. We experiment with NSS using DCGAN and StyleGAN2 based on benchmark datasets in which the NSS-based GANs outperforms the state-of-the-arts in most cases.

Code-switching (CS) is a common linguistic phenomenon exhibited by multilingual individuals, where they tend to alternate between languages within one single conversation. CS is a complex phenomenon that not only encompasses linguistic challenges, but also contains a great deal of complexity in terms of its dynamic behaviour across speakers. Given that the factors giving rise to CS vary from one country to the other, as well as from one person to the other, CS is found to be a speaker-dependant behaviour, where the frequency by which the foreign language is embedded differs across speakers. While several researchers have looked into predicting CS behaviour from a linguistic point of view, research is still lacking in the task of predicting user CS behaviour from sociological and psychological perspectives. We provide an empirical user study, where we investigate the correlations between users' CS levels and character traits. We conduct interviews with bilinguals and gather information on their profiles, including their demographics, personality traits, and traveling experiences. We then use machine learning (ML) to predict users' CS levels based on their profiles, where we identify the main influential factors in the modeling process. We experiment with both classification as well as regression tasks. Our results show that the CS behaviour is affected by the relation between speakers, travel experiences as well as Neuroticism and Extraversion personality traits.

We consider matrix factorization (MF) with certain constraints, which finds wide applications in various areas. Leveraging variational inference (VI) and unitary approximate message passing (UAMP), we develop a Bayesian approach to MF with an efficient message passing implementation, called UAMPMF. With proper priors imposed on the factor matrices, UAMPMF can be used to solve many problems that can be formulated as MF, such as non negative matrix factorization, dictionary learning, compressive sensing with matrix uncertainty, robust principal component analysis, and sparse matrix factorization. Extensive numerical examples are provided to show that UAMPMF significantly outperforms state-of-the-art algorithms in terms of recovery accuracy, robustness and computational complexity.

Market Drivers: Rising complexity and diversity of mobile networks is driving the market of deep learning. These increasing complexity has made the managing of the network difficult.

Known as OceanOneK, the robot allows its operators to feel like they're underwater explorers, too. OceanOneK resembles a human diver from the front, with arms and hands and eyes that have 3D vision, capturing the underwater world in full color. The back of the robot has computers and eight multidirectional thrusters that help it carefully maneuver the sites of fragile sunken ships. OceanOneK, here doing an experiment in a swimming pool at Stanford University, resembles a human diver. When an operator at the ocean's surface uses controls to direct OceanOneK, the robot's haptic (touch-based) feedback system causes the person to feel the water's resistance as well as the contours of artifacts.

In 1917, Marcel Duchamp submitted a sculpture to the Society of Independent Artists under a false name. Fountain was a urinal, bought from a toilet supplier, with the signature R. Mutt on its side in black paint. Duchamp wanted to see if the society would abide by its promise to accept submissions without censorship or favor. But Duchamp was also looking to broaden the notion of what art is, saying a ready-made object in the right context would qualify. Then, as before, the debate raged about if something mechanically produced – a urinal, or a soup can (albeit hand-painted by Warhol) – counted as art, and what that meant. Now, the debate has been turned upon its head, as machines can mass-produce unique pieces of art on their own.

Incorporating artificial intelligence has been a key goal for agencies across the executive branch for quite some time. But now, Congress is considering jumping on the bandwagon as well. Lawmakers on the House Select Committee on the Modernization of Congress are interested in exploring just what AI might be able to help them accomplish. Joe Mariani, a research manager for the Deloitte Center for Government Insights, told the committee during a July 28 hearing about... Incorporating artificial intelligence has been a key goal for agencies across the executive branch for quite some time. But now, Congress is considering jumping on the bandwagon as well.

Robust quantization improves the tolerance of networks for various implementations, allowing reliable output in different bit-widths or fragmented low-precision arithmetic. In this work, we perform extensive analyses to identify the sources of quantization error and present three insights to robustify a network against quantization: reduction of error propagation, range clamping for error minimization, and inherited robustness against quantization. Based on these insights, we propose two novel methods called symmetry regularization (SymReg) and saturating nonlinearity (SatNL). Applying the proposed methods during training can enhance the robustness of arbitrary neural networks against quantization on existing post-training quantization (PTQ) and quantization-aware training (QAT) algorithms and enables us to obtain a single weight flexible enough to maintain the output quality under various conditions. We conduct extensive studies on CIFAR and ImageNet datasets and validate the effectiveness of the proposed methods.