This article presents an extensive literature review of technology based intervention methodologies for individuals facing Autism Spectrum Disorder (ASD). Reviewed methodologies include: contemporary Computer Aided Systems (CAS), Computer Vision Assisted Technologies (CVAT) and Virtual Reality (VR) or Artificial Intelligence (AI)-Assisted interventions. The research over the past decade has provided enough demonstrations that individuals with ASD have a strong interest in technology based interventions, which are useful in both, clinical settings as well as at home and classrooms. Despite showing great promise, research in developing an advanced technology based intervention that is clinically quantitative for ASD is minimal. Moreover, the clinicians are generally not convinced about the potential of the technology based interventions due to non-empirical nature of published results. A major reason behind this lack of acceptability is that a vast majority of studies on distinct intervention methodologies do not follow any specific standard or research design. We conclude from our findings that there remains a gap between the research community of computer science, psychology and neuroscience to develop an AI assisted intervention technology for individuals suffering from ASD. Following the development of a standardized AI based intervention technology, a database needs to be developed, to devise effective AI algorithms.

In image classification tasks, the ability of deep CNNs to deal with complex image data has proven to be unrivalled. However, they require large amounts of labeled training data to reach their full potential. In specialised domains such as healthcare, labeled data can be difficult and expensive to obtain. Active Learning aims to alleviate this problem, by reducing the amount of labelled data needed for a specific task while delivering satisfactory performance. We propose DEBAL, a new active learning strategy designed for deep neural networks. This method improves upon the current state-of-the-art deep Bayesian active learning method, which suffers from the mode collapse problem. We correct for this deficiency by making use of the expressive power and statistical properties of model ensembles. Our proposed method manages to capture superior data uncertainty, which translates into improved classification performance. We demonstrate empirically that our ensemble method yields faster convergence of CNNs trained on the MNIST and CIFAR-10 datasets.

It is said that beauty is in the eye of the beholder. But how exactly can we characterize such discrepancies in interpretation? For example, are there any specific features of an image that makes person A regard an image as beautiful while person B finds the same image displeasing? Such questions ultimately aim at explaining our individual ways of interpretation, an intention that has been of fundamental importance to the social sciences from the beginning. More recently, advances in computer science brought up two related questions: First, can computational tools be adopted for analyzing ways of interpretation? Second, what if the "beholder" is a computer model, i.e., how can we explain a computer model's point of view? Numerous efforts have been made regarding both of these points, while many existing approaches focus on particular aspects and are still rather separate. With this paper, in order to connect these approaches we introduce a theoretical framework for analyzing interpretation, which is applicable to interpretation of both human beings and computer models. We give an overview of relevant computational approaches from various fields, and discuss the most common and promising application areas. The focus of this paper lies on interpretation of text and image data, while many of the presented approaches are applicable to other types of data as well.

Awareness of the possible impacts associated with artificial intelligence has risen in proportion to progress in the field. While there are tremendous benefits to society, many argue that there are just as many, if not more, concerns related to advanced forms of artificial intelligence. Accordingly, research into methods to develop artificial intelligence safely is increasingly important. In this paper, we provide an overview of one such safety paradigm: containment with a critical lens aimed toward generative adversarial networks and potentially malicious artificial intelligence. Additionally, we illuminate the potential for a developmental blindspot in the stovepiping of containment mechanisms.

Data collection is a major bottleneck in machine learning and an active research topic in multiple communities. There are largely two reasons data collection has recently become a critical issue. First, as machine learning is becoming more widely-used, we are seeing new applications that do not necessarily have enough labeled data. Second, unlike traditional machine learning where feature engineering is the bottleneck, deep learning techniques automatically generate features, but instead require large amounts of labeled data. Interestingly, recent research in data collection comes not only from the machine learning, natural language, and computer vision communities, but also from the data management community due to the importance of handling large amounts of data. In this survey, we perform a comprehensive study of data collection from a data management point of view. Data collection largely consists of data acquisition, data labeling, and improvement of existing data or models. We provide a research landscape of these operations, provide guidelines on which technique to use when, and identify interesting research challenges. The integration of machine learning and data management for data collection is part of a larger trend of Big data and Artificial Intelligence (AI) integration and opens many opportunities for new research.

This paper describes a novel approach of packing sparse convolutional neural networks for their efficient systolic array implementations. By combining subsets of columns in the original filter matrix associated with a convolutional layer, we increase the utilization efficiency of the systolic array substantially (e.g., ~4x) due to the increased density of nonzeros in the resulting packed filter matrix. In combining columns, for each row, all filter weights but one with the largest magnitude are pruned. We retrain the remaining weights to preserve high accuracy. We demonstrate that in mitigating data privacy concerns the retraining can be accomplished with only fractions of the original dataset (e.g., 10\% for CIFAR-10). We study the effectiveness of this joint optimization for both high utilization and classification accuracy with ASIC and FPGA designs based on efficient bit-serial implementations of multiplier-accumulators. We present analysis and empirical evidence on the superior performance of our column combining approach against prior arts under metrics such as energy efficiency (3x) and inference latency (12x).

In our work, we propose to represent HTM as a set of flat models, or layers, and a set of topical hierarchies, or edges. We suggest several quality measures for edges of hierarchical models, resembling those proposed for flat models. We conduct an assessment experimentation and show strong correlation between the proposed measures and human judgement on topical edge quality. We also introduce heterogeneous algorithm to build hierarchical topic models for heterogeneous data sources. We show how making certain adjustments to learning process helps to retain original structure of customized models while allowing for slight coherent modifications for new documents. We evaluate this approach using the proposed measures and show that the proposed heterogeneous algorithm significantly outperforms the baseline concat approach. Finally, we implement our own ESE called Rysearch, which demonstrates the potential of ARTM approach for visualizing large heterogeneous document collections.

Based on 46 in-depth interviews with scientists, engineers, and CEOs, this document presents a list of concrete machine research problems, progress on which would directly benefit tech ventures in East Africa. The goal of this work is to give machine learning researchers a fuller picture of where and how their efforts as scientists can be useful. The goal is thus not to highlight research problems that are unique to East Africa -- indeed many of the problems listed below are of general interest in machine learning. The problems on the list are united solely by the fact that technology practitioners and organizations in East Africa reported a pressing need for their solution. The author is aware that listing machine learning problems without also providing data for them is not a recipe for getting those problems solved. If the reader is interested in any of the problems below, please get in touch.

Answer set programming (ASP) is a successful declarative formalism for knowledge representation and reasoning. The evaluation of ASP programs is nowadays based on the Conflict-Driven Clause Learning (CDCL) backtracking search algorithm. Recent work suggested that the performance of CDCL-based implementations can be considerably improved on specific benchmarks by extending their solving capabilities with custom heuristics and propagators. However, embedding such algorithms into existing systems requires expert knowledge of the internals of ASP implementations. The development of effective solver extensions can be made easier by providing suitable programming interfaces. In this paper, we present the interface for extending the CDCL-based ASP solver WASP. The interface is both general, i.e. it can be used for providing either new branching heuristics and propagators, and external, i.e. the implementation of new algorithms requires no internal modifications of WASP. Moreover, we review the applications of the interface witnessing it can be successfully used to extend WASP for solving effectively hard instances of both real-world and synthetic problems. Under consideration in Theory and Practice of Logic Programming (TPLP).

Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence. Among the most common approaches are algorithms based on gradient ascent of a score function representing discounted return. In this paper, we examine the role of these policy gradient and actor-critic algorithms in partially-observable multiagent environments. We show several candidate policy update rules and relate them to a foundation of regret minimization and multiagent learning techniques for the one-shot and tabular cases, leading to previously unknown convergence guarantees. We apply our method to model-free multiagent reinforcement learning in adversarial sequential decision problems (zero-sum imperfect information games), using RL-style function approximation. We evaluate on commonly used benchmark Poker domains, showing performance against fixed policies and empirical convergence to approximate Nash equilibria in self-play with rates similar to or better than a baseline model-free algorithm for zero-sum games, without any domain-specific state space reductions.