Abstract

The convergence of Deep Reinforcement Learning (DRL) and cognitive neuroscience has opened avenues for probing neural representations within the brain. This thesis delves into the synergy between decision-making and representation by harnessing DRL’s capabilities. Through a focus on dot motion perceptual decision-making task within a high-dimensional framework akin to psychological experiments, we acquire novel insights into how intricate neural networks tackle complex tasks. The resultant end-to-end model not only elucidates network strategies, but also offers a backdrop for understanding analogous brain processes. Investigation reveals intriguing resemblances between the network’s behavior and neural mechanisms observed in the middle temporal visual area (MT) of the brain, known for encoding direction and motion strength. Remarkably, direction selectivity emerges solely through reward-driven training, while graded firing patterns encode motion strength. A testable hypothesis arises, suggesting coherenceselective neurons within the MT population. While conventional Reinforcement Learning (RL) presupposes uniform data distributions, real-world scenarios like autonomous driving and natural environments display Zipfian distributions, characterized by frequent occurrences amidst rare events. Inspired by complementary learning systems theory, this work introduces an architecture tailored for learning from Zipfian distributions. Unsupervised discovery of long tail states and their retention in episodic memory, coupled with recurrent activations, forms the core of the proposed architecture. Retrieval from episodic memory via similarity-based search, reinforced with weighted importance, amplifies performance across diverse Zipfian tasks. Our proposed architecture achieves higher accuracy than the IMPALA algorithm across all three tasks and evaluation metrics (Zipfian, Uniform, and Rare Accuracy). This thesis advances the nexus of decision-making and neural representation through DRL, while proposing an innovative architecture capable of navigating the intricacies of Zipfian data distributions. It not only augments our grasp of cognitive building blocks but also bears implications for resolving challenges across real-world domains. This research in one small step that bridges the gap between computational models and cognitive processes, opening new vistas for understanding and application.

Abstract

Insurance plays a vital role in safeguarding individuals and businesses against various risks. Understanding the factors that influence insurance consumption is crucial for policymakers, insurance companies, and consumers alike. This thesis examines various aspects of insurance demand, focusing on understanding consumer behaviour related to insurance purchase decisions. Two studies were conducted in this work. The first study investigated the influence of wealth level on insurance consumption behavior using a game application. The results showed a nonlinear correlation between wealth and insurance consumption, increasing with increasing wealth and achieving a negative correlation after a threshold. The second study used a game-like application to determine how various behavioral characteristics, such as risk tolerance and loss framing, affect the decision to purchase insurance. The study focused on university students aged 18 to 25 with no income and working-class people aged 35 to 55. The results showed that the effect of loss framing on insurance consumption depends on the particular insurance policy, even if participants are aware of the loss. The studies explore data collection methods using surveys and game-like applications for studying insurance consumption behavior. Surveys can lead to dishonest responses, misunderstandings, and errors in interpretation. Gaming applications offer a more authentic and ecologically valid context, framing, capturing real-time behaviors and decision-making. These applications capture various aspects of insurance consumption behavior, such as decision-making processes, choices, and engagement patterns. The findings can be directly extrapolated or modeled to predict human behavior in real-life situations.

Abstract

In the realm of open-domain question answering, a common challenge arises from the inherent ambiguity of user queries. Conventional question-answering systems that offer a single answer often falter when confronted with ambiguity, as questions may be subject to multiple interpretations and yield various distinct answers. This paper addresses this challenge through the lens of multi-answer retrieval, a task focused on retrieving passages capable of capturing the diverse array of answers to a single question. Our approach introduces a re-ranking methodology that leverages Determinantal point processes, employing BERT embeddings as kernels. This technique takes a holistic view by jointly considering both query-passage relevance and passage-passage correlation. The goal is to retrieve passages that not only align with the user’s query but also encompass a diversity of information. Empirical results underscore the effectiveness of our re-ranking approach, demonstrating its superiority over state-of-the-art methods, particularly when evaluated on the AmbigQA dataset. In parallel, the field of question-answering, powered by reader models or answer generation, has seen significant advancements. Neural sequence-to-sequence models, especially those incorporating attention mechanisms, have played a vital role in this progress. However, these models encounter a limitation as they predominantly rely on pointer generators that exclusively target words from the source passage, even though their goal is to provide answers that involve both the question and the source text. To address this constraint, we introduce an innovative query pointer module within a comprehensive multipointer generator framework. This module facilitates the generation of answers that combine question and passage information in diverse ways, resulting in contextually relevant responses that effectively address the nuances of user queries. Our model demonstrates a significant improvement of 3.5 points in Rouge-L scores when compared to the state-of-the-art model on existing datasets. These advancements collectively signify substantial progress in both multi-answer retrieval and question-answering research, offering the promise of enhanced capabilities in information retrieval, natural language understanding, and content summarization.

Abstract

The utilization of quantum mechanical characteristics such as entanglement serves as a critical foundation in a multitude of quantum information processing tasks. With the objective of designing quantum networks, broadcasting - which is defined as the process of producing more quantum mechanical resources from a limited amount - presents an encouraging approach. One promising method of achieving broadcasting in quantum mechanical systems is through cloning operations. This thesis delves into the investigation of broadcasting of a class of quantum entangled states that go beyond 2 ⊗ 2 systems. It is known that beyond 2⊗2 and 2⊗3 dimensional quantum systems, Peres-Horodecki criterion is no longer sufficient to detect separability of quantum states. This is because there exists entangled states with both positive and negative partial transpose (PPT and NPT). Further, it is also true that all PPT entangled states are bound entangled states. However, in the class of NPT states, there can exist bound entangled states as well as free entangled states. All free/useful/distillable entanglement is a part of the class of NPT entangled states. In this thesis, the question is asked that given an NPT entangled state in 3 ⊗ 3 dimensional system as a resource, how much entanglement can we broadcast so that resource still remains NPT. The initial chapter offers a brief overview of the historical occurrences surrounding the evolution of Quantum mechanics. It is followed by a brief and succinct introduction to the necessary theory and mathematical tools required for this thesis. In the next chapter a 3 ⊗ 3 system is chosen as a first step to understand broadcasting of NPT states in higher dimensional systems. In particular, we find out the range of broadcasting of NPT entanglement for Two parameter Class of States (TPCS) and Isotropic States (IS). Interestingly, as a derivative of this process we are also able to locate the existence of absolute PPT states (ABPPT) in 3⊗3 dimensional system. Here we implement the strategy of broadcasting through approximate cloning operations

Abstract

The recent surge in healthcare sensing technologies has revolutionized the landscape of patient care and safety monitoring. This thesis delves into the burgeoning field of healthcare sensing and addresses the critical need for advancements in monitoring systems applicable to various domains, including elderly care, critical care units, and prolonged home monitoring. These applications necessitate the continuous and non-intrusive measurement of vital signs such as heart rate, blood-oxygen saturation, temperature, and subject movement. This research focuses on enhancing patient comfort and convenience by introducing innovative solutions. Firstly, the thesis introduces a receiver front-end integrated circuit (IC) tailored for radar systems enabling non-contact-based measurement of vital signs. This radar-based approach offers a non-invasive method for obtaining crucial health parameters, promising increased accuracy and reliability while minimizing patient discomfort. Furthermore, in response to the growing demand for portable safety systems in industrial settings, the thesis presents the development of a portable industry safety system. This system is designed to provide comprehensive safety monitoring in industrial environments, ensuring the well-being of workers through real-time monitoring and hazard detection. Through the exploration of these technological advancements, this thesis contributes to the field of healthcare sensing and safety systems. The proposed receiver front-end IC for radar-based vitals monitoring offers a novel approach to non-contact sensing, while the portable industry safety system aims to enhance workplace safety through continuous monitoring and hazard detection. Overall, these advancements pave the way for improved healthcare monitoring and industrial safety, addressing critical needs in both domains.

Abstract

In the field of aerial transport, specifically in operations involving quadrotors carrying suspended payloads, two critical stages are the attachment and detachment of the payload. These procedures are challenging due to various uncertainties inherent in the quadrotor, environmental variables, and payload swings caused by human or external interactions. These uncertainties can escalate quickly, posing significant risks to the quadrotor and payload and, crucially, to the human operator involved in the attachment/detachment process. Current advanced controllers in this field often need to adequately address these uncertainties, typically treating them as bounded, predictable variables. However, this approach must be revised to manage the unpredictable nature of payload swings during these critical stages. To overcome this limitation, our research introduces an innovative adaptive anti-swing controller. This controller uniquely considers uncertainties state-dependently, specifically tailored to address swing induced by the unpredictable aspects of attaching and detaching suspended payloads. In this work, we have conducted a thorough analytical evaluation of the closed-loop stability of this new system. Additionally, real-time experimental trials have been carried out. The results from these experiments demonstrate a marked performance improvement compared to existing state-of-the-art systems. This novel approach shows promise in enhancing safety and control effectiveness in aerial payload transportation, especially during the vital phases of payload and unclasping.

Abstract

Major goal of this thesis is to study the dialectal variations and improve the performance of speech recognition with an embeddings derived from improved dialect classification system. Initial studies focused on improvement of the dialect classification system with three major dialects (AU:Australian, UK:Britain, and US:American) of English. In order to improve the performance of dialect classification system and based on the analysis of dialectal variations, advanced signal processing approaches were proposed to investigate for dialect classification with traditional i-vector system. The features that provide high spectral resolution will help to capture subtle differences between dialects. So, this thesis proposed to use single frequency filtering (SFF) and zero-time windowing (ZTW) based features that provide high spectral resolution without compromising temporal resolution. Along with frame level spectral resolution, longer temporal context will constitute for dialect classification. So, approaches that enhance the temporal context of proposed features (SFF and ZTW) approaches such as delta and double delta coefficients (∆+∆∆), shifted delta coefficients (SDCs) are experimented. It is observed that dialect classification system has given promising performance with the proposed features with temporal context provided by ∆+∆∆ and SDCs. Further, signal processing approaches that can provide long temporal summarization such as frequency domain linear prediction (FDLP) are proposed for dialect classification. From experiments, with FDLP based features, it is observed that long temporal summarization provided by FDLP based features is advantageous for discriminating dialects. So, both the signal processing approaches that provide high spectral resolution (SFF and ZTW) and long temporal summarization (FDLP) have shown to give promising performance in dialect classification when compared to commonly used STFT based features. Further, due to promising performance by deep neural networks in classification tasks and its ability to provide longer temporal context, simpler (CNN) to advanced deep neural network (TCN, TDNN, and ECAPA-TDNN) architectures that provide different temporal contexts are investigated, it is observed that advanced neural network architectures improved the performance of dialect classification. Further, on evaluation of the best of both stages, it is observed that ECAPA-TDNN performed better with proposed features (SFF). The dialectal variations in speech degrade the performance of multi-dialectal automatic speech recognition (ASR) system. The embeddings derived from the best dialect classification system are applied to multi-dialect (with AU, UK, and US dialects) ASR and found to improve the performance of the ASR system. In most studies, Indian English is considered as a single dialect even though it has different native speakers. So, the inclusion of foreign dialectal embeddings improved the performance of the ASR system. The observations made in dialect classification systems with major dialects of English are extended to foreign dialect classification (i.e., native language (or L1) identification). The embeddings extracted from the improved dialect classification system are included along with the Indian English ASR system to improve the performance.

Abstract

About 57% of the land area in India lies within the moderate-to-severe seismic zone, where approximately 80% of the population resides. Consequently, a substantial proportion of India's buildings are at risk due to seismic hazard and building stock in seismically active regions. The pre-earthquake safety assessment of the built environment plays a crucial role in mitigating damage and losses by identifying structures that are susceptible to earthquakes and implementing suitable measures to minimize their impact. The process of rapid visual screening (RVS) plays a vital role in evaluating the seismic vulnerability and potential risks of existing buildings in urban areas. The preservation and safety of existing buildings assume greater significance as urban areas undergo continuous growth and expansion. The Rapid Visual Survey (RVS) is a crucial instrument used to identify structures that necessitate more comprehensive assessment and potential retrofitting in order to improve their ability to withstand seismic activity. In the present study, a total of 15 reinforced concrete framed buildings of above 10 m. Height were selected randomly from nearly 6 different locations in Vijayawada city falling in Seismic Zone III. Studies for Rapid Visual Assessments as well as detailed assessment were conducted and the results of both assessments are discussed. The study finds: (i) the construction practices in India must be checked regularly and also must evaluated regularly; (ii) there is urgent need to spread the awareness among engineers and builders about the seismic code provisions and municipal guidelines.

Abstract

The digital age presents an overwhelming deluge of multimodal data, underscoring the imperative need for effective text summarization techniques. Such techniques transform vast amounts of textual and visual data into concise, comprehensible, and insightful summaries, facilitating information retrieval, comprehension, and decision-making. This thesis pioneers innovative strategies to enhance text summarization by employing various forms of contextual guidance and multimodal data, contributing significantly to the evolution of the field and offering a cohesive narrative that links these diverse yet interconnected areas of study. The journey begins with an exploration of ”Popularity Forecasting” of sentences within news articles. This novel approach surpasses traditional salience-based extractive summarization by predicting the ’popularity’ or ’eye-catching’ potential of sentences. We create a popularity dataset which contains news articles from CNN/DM[47] with their sentence-popularity score mapping. We create this by comparing sentences with the search queries for the particular article. Then we adapt trained extractive summarizers to perform regression tasks and predict the popularity of a particular sentence within a news article. The result is a ranking of sentences based on their popularity scores Next, the research advances into the realm of ”Multimodal Summarization,” which synergizes textual and visual elements to create a more holistic summary. By pairing concise textual summaries with the most salient images from news articles, this technique delivers a richer and more comprehensive understanding of the content. In this work we also show that we can improve the accuracy of summarization models by using images to aid the summarization process. To do this we utilize visuolinguistic transformers like CLIP[54], OSCAR[36] to help in the interaction of the two modalities and we adapt general summarization models so that we can incorporate both textual and visual information in the summarization model Building on the foundation of extractive summarization, and using the core logic from the multimodal summarization work the study then introduces ”Guided Summarization.” This innovative method uses salience scores of sentences, obtained from an extractive summarizer, to guide an abstractive summarizer. This symbiotic relationship between the two forms of summarization results in more contextually relevant and focused abstract summaries. The research further pushes the boundaries of personalization with ”Persona-based Summarization,” applied to SEBI legal case files. This technique generates tailored summaries based on the specific information needs of different personas such as investors, defense lawyers, and judges. It underscores the potential of personalization in text summarization, making the information more accessible and relevant to each user profile. Finally, building on the insights gleaned from the exploration of multimodal summarization, the study culminates with the creation of an ”Indic Multimodal Text-Image Pair Dataset.” This unique resource is a rich assembly of text and image pairs of different Indian languages, serving as a critical foundation for the development and evaluation of visuolinguistic transformers, especially those focusing on data from the Indian subcontinent. In summary, this thesis provides a comprehensive exploration of how contextual guidance and multimodal data can significantly enhance text summarization. The innovative techniques and resources proposed and developed in this research, connected through a cohesive narrative, promise to significantly advance the field of text summarization, paving the way for more engaging, comprehensive, and personalized summary generation

Abstract

In the realm of biometric security, face recognition technology plays an increasingly pivotal role. However, as its adoption grows, so does the need to safeguard it against adversarial attacks. Attacks involve presenting images of a person printed on a medium or displayed on a screen. Detection of such attacks relies on identifying artifacts introduced in the image during the printing or display and capture process. Adversarial Attacks try to deceive the learning strategy of a recognition system using slight modifications to the captured image. Evaluating the risk level of adversarial images is essential for safely deploying face authentication models in the real world. Among these, physical adversarial attacks present a particularly insidious threat to face antispoofing systems. Popular approaches for physical-world attacks, such as print or replay attacks, suffer from some limitations, like including physical and geometrical artifacts. The presence of a physical process (printing and capture) between the image generation and the PAD module makes traditional adversarial attacks non-viable. Recently adversarial attacks have gained attraction, which try to digitally deceive the learning strategy of a recognition system using slight modifications to the captured image. While most previous research assumes that the adversarial image could be digitally fed into the authentication systems, this is not always the case for systems deployed in the real world. This thesis delves into the intriguing domain of physical adversarial attacks on face antispoofing systems, aiming to expose their vulnerabilities and implications. Our research unveils novel methodologies using white box and black box approaches to craft adversarial inputs capable of deceiving even the most robust face antispoofing systems. Unlike traditional adversarial attacks that manipulate digital inputs, our approach operates in the physical domain, where printed images and replayed videos are utilized to mimic real-world presentation attacks. By dissecting and understanding the vulnerabilities inherent in face antispoofing systems, we can develop more resilient defenses, contributing to the security of biometric authentication in an increasingly interconnected world. This thesis not only highlights the pressing need to address these vulnerabilities but also motivates towards a pioneering approach by exploring simple yet effective attack strategy to advancing the state of the art in face antispoofing security.