No abstract

Background: Schizophrenia, a severe psychological disorder, shows symptoms such as hallucinations and delusions. In addition, patients with schizophrenia often exhibit a deficit in working memory which adversely impacts the attentiveness and the behavioral characteristics of a person. Although several clinical efforts have already been made to study working memory deficit in schizophrenia, in this paper, we investigate the applicability of a machine learning approach for identification of the brain regions that get affected by schizophrenia leading to the dysfunction of the working memory. Methods: We propose a novel scheme for identification of the affected brain regions from functional magnetic resonance imaging data by deploying group independent component analysis in conjunction with feature extraction based on statistical measures, followed by sequential forward feature selection. The features that show highest accuracy during the classification between healthy and schizophrenia subjects are selected. Results: This study reveals several brain regions like cerebellum, inferior temporal gyrus, superior temporal gyrus, superior frontal gyrus, insula, and amygdala that have been reported in the existing literature, thus validating the proposed approach. We are also able to identify some functional changes in the brain regions, such as Heschl gyrus and the vermian area, which have not been reported in the literature involving working memory studies amongst schizophrenia patients. Conclusions: As our study confirms the results obtained in earlier studies, in addition to pointing out some brain regions not reported in earlier studies, the findings are likely to serve as a cue for clinical investigation, leading to better medical intervention.

No abstract

One of the long standing goals of Artificial Intelligence (AI) is to build cognitive agents which can perform complex tasks from raw sensory inputs without explicit supervision. Recent progress in combining Reinforcement Learning objective functions and Deep Learning architectures has achieved promising results for such tasks. An important aspect of such sequential decision making problems, which has largely been neglected, is for the agent to decide on the duration of time for which to commit to actions. Such action repetition is important for computational efficiency, which is necessary for the agent to respond in real-time to events (in applications such as self-driving cars). Action Repetition arises naturally in real life as well as simulated environments. The time scale of executing an action enables an agent (both humans and AI) to decide the granularity of control during task execution. Current state of the art Deep Reinforcement Learning models, whether they are off-policy or on-policy, consist of a framework with a static action repetition paradigm, wherein the action decided by the agent is repeated for a fixed number of time steps regardless of the contextual state while executing the task. In this paper, we propose a new framework - Dynamic Action Repetition which changes Action Repetition Rate (the time scale of repeating an action) from a hyper-parameter of an algorithm to a dynamically learnable quantity. At every decision-making step, our models allow the agent to commit to an action and the time scale of executing the action. We show empirically that such a dynamic time scale mechanism improves the performance on relatively harder games in the Atari 2600 domain, independent of the underlying Deep Reinforcement Learning algorithm used.

The intertwining of chemoinformatics with artificial intelligence (AI) has given a tremendous fillip to the field of drug discovery. With the rapid growth of chemical data from high throughput screening and combinatorial synthesis, AI has become an indispensable tool for drug designers to mine chemical information from large compound databases for developing drugs at a much faster rate as never before. The applications of AI have gone beyond bioactivity predictions and have shown promise in addressing diverse problems in drug discovery like de novo molecular design, synthesis prediction and biological image analysis. In this article, we provide an overview of all the algorithms under the umbrella of AI, enlist the tools/frameworks required for implementing these algorithms as well as present a compendium of web servers, databases and open-source platforms implicated in drug discovery, Quantitative Structure-Activity Relationship (QSAR), data mining, solvation free energy and molecular graph mining.