This paper presents a novel framework for Speech Activity Detection (SAD). Inspired by the recent success of multi-task learning approaches in the speech processing domain, we propose a novel joint learning framework for SAD. We utilise generative adversarial networks to automatically learn a loss function for joint prediction of the frame-wise speech/ non-speech classifications together with the next audio segment. In order to exploit the temporal relationships within the input signal, we propose a temporal discriminator which aims to ensure that the predicted signal is temporally consistent. We evaluate the proposed framework on multiple public benchmarks, including NIST OpenSAT' 17, AMI Meeting and HAVIC, where we demonstrate its capability to outperform state-of-the-art SAD approaches. Furthermore, our cross-database evaluations demonstrate the robustness of the proposed approach across different languages, accents, and acoustic environments.

Predicting whether a chemical structure shares a desired biological effect can have a significant impact for in-silico compound screening in early drug discovery. In this study, we developed a deep learning model where compound structures are represented as graphs and then linked to their biological footprint. To make this complex problem computationally tractable, compound differences were mapped to biological effect alterations using Siamese Graph Convolutional Neural Networks. The proposed model was able to learn new representations from chemical structures and identify structurally dissimilar compounds that affect similar biological processes with high precision. Additionally, by utilizing deep ensembles to estimate uncertainty, we were able to provide reliable and accurate predictions for chemical structures that are very different from the ones used during training. Finally, we present a novel inference approach, where the trained models are used to estimate the signaling pathways affected by a compound perturbation in a specific cell line, using only its chemical structure as input. As a use case, this approach was used to infer signaling pathways affected by FDA-approved anticancer drugs.

We investigate how different active learning (AL) query policies coupled with classification uncertainty visualizations affect analyst trust in automated classification systems. A current standard policy for AL is to query the oracle (e.g., the analyst) to refine labels for datapoints where the classifier has the highest uncertainty. This is an optimal policy for the automation system as it yields maximal information gain. However, model-centric policies neglect the effects of this uncertainty on the human component of the system and the consequent manner in which the human will interact with the system post-training. In this paper, we present an empirical study evaluating how AL query policies and visualizations lending transparency to classification influence trust in automated classification of image data. We found that query policy significantly influences an analyst's trust in an image classification system, and we use these results to propose a set of oracle query policies and visualizations for use during AL training phases that can influence analyst trust in classification.

We propose spectral methods for long-term forecasting of temporal signals stemming from linear and nonlinear quasi-periodic dynamical systems. For linear signals, we introduce an algorithm with similarities to the Fourier transform but which does not rely on periodicity assumptions, allowing for forecasting given potentially arbitrary sampling intervals. We then extend this algorithm to handle nonlinearities by leveraging Koopman theory. The resulting algorithm performs a spectral decomposition in a nonlinear, data-dependent basis. The optimization objective for both algorithms is highly non-convex. However, expressing the objective in the frequency domain allows us to compute global optima of the error surface in a scalable and efficient manner, partially by exploiting the computational properties of the Fast Fourier Transform. Because of their close relation to Bayesian Spectral Analysis, uncertainty quantification metrics are a natural byproduct of the spectral forecasting methods.

Data poisoning--the process by which an attacker takes control of a model by making imperceptible changes to a subset of the training data--is an emerging threat in the context of neural networks. Existing attacks for data poisoning have relied on hand-crafted heuristics. Instead, we pose crafting poisons more generally as a bi-level optimization problem, where the inner level corresponds to training a network on a poisoned dataset and the outer level corresponds to updating those poisons to achieve a desired behavior on the trained model. We then propose MetaPoison, a first-order method to solve this optimization quickly. MetaPoison is effective: it outperforms previous clean-label poisoning methods by a large margin under the same setting. MetaPoison is robust: its poisons transfer to a variety of victims with unknown hyperparameters and architectures. MetaPoison is also general-purpose, working not only in fine-tuning scenarios, but also for end-to-end training from scratch with remarkable success, e.g. causing a target image to be misclassified 90% of the time via manipulating just 1% of the dataset. Additionally, MetaPoison can achieve arbitrary adversary goals not previously possible--like using poisons of one class to make a target image don the label of another arbitrarily chosen class. Finally, MetaPoison works in the real-world. We demonstrate successful data poisoning of models trained on Google Cloud AutoML Vision. Code and premade poisons are provided at https://github.com/wronnyhuang/metapoison

Shimla: Under its National Mission on Interdisciplinary Cyber-Physical Systems (NM-ICPS), the Department of Science and Technology (DST) has sanctioned Rs 7.25 crore to IIT Mandi to establish a Technology Innovation Hub (TIH) at the Institute. The focus of the TIH in IIT Mandi will be research on human-computer interaction (HCI), where projects will highlight the design and development of computer technology (interfaces) and the study of the interaction between users and computers. Being the youngest IIT in the country, IIT Mandi is the only institute to have a cell under HCI theme. " Human-Computer Interface as a theme will focus a step ahead than normal usage of systems by humans. The institute will create technology that will make computer interaction much easier and natural for the users", says Dr Varun Dutt, Principal Investigator, TIH, IIT Mandi.

Newswire) VSBLTY Groupe Technologies Corp. (CSE: VSBY) (Frankfurt: 5VS) (OTC: VSBGF) ("VSBLTY"), a leading retail software and technology company, and RadarApp, a Smart City Solutions provider, are now testing crowd temperature scanning as a tool to help identify potential at risk individuals and ultimately reduce the spread of disease. The testing was launched at the urging of Mexico City officials who are investing in the safety kits and integrated security program that is already proving successful in reducing crime. As previously announced, the firms are installing thousands of security kits, powered by VSBLTY software, in the initial phase of the "Smart City" intelligent camera network program, RADAR. VSBLTY previously announced this deal to have a projected three-year value of $10M USD. In addition to a remarkable impact on crime reduction, VSBLTY is working with RadarApp to test the addition of infrared camera capability that enables temperature scanning of crowds in various locations along with a correlation to face capture.

This research paper explores the performance of Machine Learning (ML) algorithms and techniques that can be used for financial asset price forecasting. The prediction and forecasting of asset prices and returns remains one of the most challenging and exciting problems for quantitative finance and practitioners alike. The massive increase in data generated and captured in recent years presents an opportunity to leverage Machine Learning algorithms. This study directly compares and contrasts state-of-the-art implementations of modern Machine Learning algorithms on high performance computing (HPC) infrastructures versus the traditional and highly popular Capital Asset Pricing Model (CAPM) on U.S equities data. The implemented Machine Learning models - trained on time series data for an entire stock universe (in addition to exogenous macroeconomic variables) significantly outperform the CAPM on out-of-sample (OOS) test data.

Researchers have long been interested in the role that norms can play in governing agent actions in multi-agent systems. Much work has been done on formalising normative concepts from human society and adapting them for the government of open software systems, and on the simulation of normative processes in human and artificial societies. However, there has been comparatively little work on applying normative MAS mechanisms to understanding the norms in human society. This work investigates this issue in the context of international politics. Using the GDELT dataset, containing machine-encoded records of international events extracted from news reports, we extracted bilateral sequences of inter-country events and applied a Bayesian norm mining mechanism to identify norms that best explained the observed behaviour. A statistical evaluation showed that the normative model fitted the data significantly better than a probabilistic discrete event model.

A small subset of explainability techniques developed initially for image recognition models has recently been applied for interpretability of 3D Convolutional Neural Network models in activity recognition tasks. Much like the models themselves, the techniques require little or no modification to be compatible with 3D inputs. However, these explanation techniques regard spatial and temporal information jointly. Therefore, using such explanation techniques, a user cannot explicitly distinguish the role of motion in a 3D model's decision. In fact, it has been shown that these models do not appropriately factor motion information into their decision. We propose a selective relevance method for adapting the 2D explanation techniques to provide motion-specific explanations, better aligning them with the human understanding of motion as conceptually separate from static spatial features. We demonstrate the utility of our method in conjunction with several widely-used 2D explanation methods, and show that it improves explanation selectivity for motion. Our results show that the selective relevance method can not only provide insight on the role played by motion in the model's decision -- in effect, revealing and quantifying the model's spatial bias -- but the method also simplifies the resulting explanations for human consumption.