In the field of machine learning, reinforcement learning stands out for its ability to explore approaches to complex, high dimensional problems that outperform even expert humans. For robotic locomotion tasks reinforcement learning provides an approach to solving them without the need for unique controllers. In this thesis, two reinforcement learning algorithms, Deep Deterministic Policy Gradient and Group Factor Policy Search are compared based upon their performance in the bipedal walking environment provided by OpenAI gym. These algorithms are evaluated on their performance in the environment and their sample efficiency.

Visual processing in social media platforms is a key step in gathering and understanding information in the era of Internet and big data. Online data is rich in content, but its processing faces many challenges including: varying scales for objects of interest, unreliable and/or missing labels, the inadequacy of single modal data and difficulty in analyzing high dimensional data. Towards facilitating the processing and understanding of online data, this dissertation primarily focuses on three challenges that I feel are of great practical importance: handling scale differences in computer vision tasks, such as facial component detection and face retrieval, developing efficient classifiers using partially labeled data and noisy data, and employing multi-modal models and feature selection to improve multi-view data analysis. For the first challenge, I propose a scale-insensitive algorithm to expedite and accurately detect facial landmarks. For the second challenge, I propose two algorithms that can be used to learn from partially labeled data and noisy data respectively. For the third challenge, I propose a new framework that incorporates feature selection modules into LDA models.

Virtual digital assistants are automated software systems which assist humans by understanding natural languages such as English, either in voice or textual form. In recent times, a lot of digital applications have shifted towards providing a user experience using natural language interface. The change is brought up by the degree of ease with which the virtual digital assistants such as Google Assistant and Amazon Alexa can be integrated into your application. These assistants make use of a Natural Language Understanding (NLU) system which acts as an interface to translate unstructured natural language data into a structured form. Such an NLU system uses an intent finding algorithm which gives a high-level idea or meaning of a user query, termed as intent classification. The intent classification step identifies the action(s) that a user wants the assistant to perform. The intent classification step is followed by an entity recognition step in which the entities in the utterance are identified on which the intended action is performed. This step can be viewed as a sequence labeling task which maps an input word sequence into a corresponding sequence of slot labels. This step is also termed as slot filling.

In this thesis, we improve the intent classification and slot filling in the virtual voice agents by automatic data augmentation. Spoken Language Understanding systems face the issue of data sparsity. The reason behind this is that it is hard for a human-created training sample to represent all the patterns in the language. Due to the lack of relevant data, deep learning methods are unable to generalize the Spoken Language Understanding model. This thesis expounds a way to overcome the issue of data sparsity in deep learning approaches on Spoken Language Understanding tasks. Here we have described the limitations in the current intent classifiers and how the proposed algorithm uses existing knowledge bases to overcome those limitations. The method helps in creating a more robust intent classifier and slot filling system.

Multimodal Representation Learning is a multi-disciplinary research field which aims to integrate information from multiple communicative modalities in a meaningful manner to help solve some downstream task. These modalities can be visual, acoustic, linguistic, haptic etc. The interpretation of ’meaningful integration of information from different modalities’ remains modality and task dependent. The downstream task can range from understanding one modality in the presence of information from other modalities, to that of translating input from one modality to another. In this thesis the utility of multimodal representation learning for understanding one modality vis-à-vis Image Understanding for Visual Reasoning given corresponding information in other modalities, as well as translating from one modality to the other, specifically, Text to Image Translation was investigated.

Visual Reasoning has been an active area of research in computer vision. It encompasses advanced image processing and artificial intelligence techniques to locate, characterize and recognize objects, regions and their attributes in the image in order to comprehend the image itself. One way of building a visual reasoning system is to ask the system to answer questions about the image that requires attribute identification, counting, comparison, multi-step attention, and reasoning. An intelligent system is thought to have a proper grasp of the image if it can answer said questions correctly and provide a valid reasoning for the given answers. In this work how a system can be built by learning a multimodal representation between the stated image and the questions was investigated. Also, how background knowledge, specifically scene-graph information, if available, can be incorporated into existing image understanding models was demonstrated.

Multimodal learning provides an intuitive way of learning a joint representation between different modalities. Such a joint representation can be used to translate from one modality to the other. It also gives way to learning a shared representation between these varied modalities and allows to provide meaning to what this shared representation should capture. In this work, using the surrogate task of text to image translation, neural network based architectures to learn a shared representation between these two modalities was investigated. Also, the ability that such a shared representation is capable of capturing parts of different modalities that are equivalent in some sense is proposed. Specifically, given an image and a semantic description of certain objects present in the image, a shared representation between the text and the image modality capable of capturing parts of the image being mentioned in the text was demonstrated. Such a capability was showcased on a publicly available dataset.

Mixed reality mobile platforms co-locate virtual objects with physical spaces, creating immersive user experiences. To create visual harmony between virtual and physical spaces, the virtual scene must be accurately illuminated with realistic physical lighting. To this end, a system was designed that Generates Light Estimation Across Mixed-reality (GLEAM) devices to continually sense realistic lighting of a physical scene in all directions. GLEAM optionally operate across multiple mobile mixed-reality devices to leverage collaborative multi-viewpoint sensing for improved estimation. The system implements policies that prioritize resolution, coverage, or update interval of the illumination estimation depending on the situational needs of the virtual scene and physical environment.

To evaluate the runtime performance and perceptual efficacy of the system, GLEAM was implemented on the Unity 3D Game Engine. The implementation was deployed on Android and iOS devices. On these implementations, GLEAM can prioritize dynamic estimation with update intervals as low as 15 ms or prioritize high spatial quality with update intervals of 200 ms. User studies across 99 participants and 26 scene comparisons reported a preference towards GLEAM over other lighting techniques in 66.67% of the presented augmented scenes and indifference in 12.57% of the scenes. A controlled lighting user study on 18 participants revealed a general preference for policies that strike a balance between resolution and update rate.

In recent years, deep learning systems have outperformed traditional machine learning systems in most domains. There has been a lot of research recently in the field of hand gesture recognition using wearable sensors due to the numerous advantages these systems have over vision-based ones. However, due to the lack of extensive datasets and the nature of the Inertial Measurement Unit (IMU) data, there are difficulties in applying deep learning techniques to them. Although many machine learning models have good accuracy, most of them assume that training data is available for every user while other works that do not require user data have lower accuracies. MirrorGen is a technique which uses wearable sensor data and generates synthetic videos using hand movements and it mitigates the traditional challenges of vision based recognition such as occlusion, lighting restrictions, lack of viewpoint variations, and environmental noise. In addition, MirrorGen allows for user-independent recognition involving minimal human effort during data collection. It also helps leverage the advances in vision-based recognition by using various techniques like optical flow extraction, 3D convolution. Projecting the orientation (IMU) information to a video helps in gaining position information of the hands. To validate these claims, we perform entropy analysis on various configurations such as raw data, stick model, hand model and real video. Human hand model is found to have an optimal entropy that helps in achieving user independent recognition. It also serves as a pervasive option as opposed to a video-based recognition. The average user independent recognition accuracy of 99.03% was achieved for a sign language dataset with 59 different users, 20 different signs with 20 repetitions each for a total of 23k training instances. Moreover, synthetic videos can be used to augment real videos to improve recognition accuracy.

Reinforcement learning (RL) is a powerful methodology for teaching autonomous agents complex behaviors and skills. A critical component in most RL algorithms is the reward function -- a mathematical function that provides numerical estimates for desirable and undesirable states. Typically, the reward function must be hand-designed by a human expert and, as a result, the scope of a robot's autonomy and ability to safely explore and learn in new and unforeseen environments is constrained by the specifics of the designed reward function. In this thesis, I design and implement a stateful collision anticipation model with powerful predictive capability based upon my research of sequential data modeling and modern recurrent neural networks. I also develop deep reinforcement learning methods whose rewards are generated by self-supervised training and intrinsic signals. The main objective is to work towards the development of resilient robots that can learn to anticipate and avoid damaging interactions by combining visual and proprioceptive cues from internal sensors. The introduced solutions are inspired by pain pathways in humans and animals, because such pathways are known to guide decision-making processes and promote self-preservation. A new "robot dodge ball' benchmark is introduced in order to test the validity of the developed algorithms in dynamic environments.

Handwritten documents have gained popularity in various domains including education and business. A key task in analyzing a complex document is to distinguish between various content types such as text, math, graphics, tables and so on. For example, one such aspect could be a region on the document with a mathematical expression; in this case, the label would be math. This differentiation facilitates the performance of specific recognition tasks depending on the content type. We hypothesize that the recognition accuracy of the subsequent tasks such as textual, math, and shape recognition will increase, further leading to a better analysis of the document.

Content detection on handwritten documents assigns a particular class to a homogeneous portion of the document. To complete this task, a set of handwritten solutions was digitally collected from middle school students located in two different geographical regions in 2017 and 2018. This research discusses the methods to collect, pre-process and detect content type in the collected handwritten documents. A total of 4049 documents were extracted in the form of image, and json format; and were labelled using an object labelling software with tags being text, math, diagram, cross out, table, graph, tick mark, arrow, and doodle. The labelled images were fed to the Tensorflow’s object detection API to learn a neural network model. We show our results from two neural networks models, Faster Region-based Convolutional Neural Network (Faster R-CNN) and Single Shot detection model (SSD).

Image Understanding is a long-established discipline in computer vision, which encompasses a body of advanced image processing techniques, that are used to locate (“where”), characterize and recognize (“what”) objects, regions, and their attributes in the image. However, the notion of “understanding” (and the goal of artificial intelligent machines) goes beyond factual recall of the recognized components and includes reasoning and thinking beyond what can be seen (or perceived). Understanding is often evaluated by asking questions of increasing difficulty. Thus, the expected functionalities of an intelligent Image Understanding system can be expressed in terms of the functionalities that are required to answer questions about an image. Answering questions about images require primarily three components: Image Understanding, question (natural language) understanding, and reasoning based on knowledge. Any question, asking beyond what can be directly seen, requires modeling of commonsense (or background/ontological/factual) knowledge and reasoning.

Knowledge and reasoning have seen scarce use in image understanding applications. In this thesis, we demonstrate the utilities of incorporating background knowledge and using explicit reasoning in image understanding applications. We first present a comprehensive survey of the previous work that utilized background knowledge and reasoning in understanding images. This survey outlines the limited use of commonsense knowledge in high-level applications. We then present a set of vision and reasoning-based methods to solve several applications and show that these approaches benefit in terms of accuracy and interpretability from the explicit use of knowledge and reasoning. We propose novel knowledge representations of image, knowledge acquisition methods, and a new implementation of an efficient probabilistic logical reasoning engine that can utilize publicly available commonsense knowledge to solve applications such as visual question answering, image puzzles. Additionally, we identify the need for new datasets that explicitly require external commonsense knowledge to solve. We propose the new task of Image Riddles, which requires a combination of vision, and reasoning based on ontological knowledge; and we collect a sufficiently large dataset to serve as an ideal testbed for vision and reasoning research. Lastly, we propose end-to-end deep architectures that can combine vision, knowledge and reasoning modules together and achieve large performance boosts over state-of-the-art methods.

Network mining has been attracting a lot of research attention because of the prevalence of networks. As the world is becoming increasingly connected and correlated, networks arising from inter-dependent application domains are often collected from different sources, forming the so-called multi-sourced networks. Examples of such multi-sourced networks include critical infrastructure networks, multi-platform social networks, cross-domain collaboration networks, and many more. Compared with single-sourced network, multi-sourced networks bear more complex structures and therefore could potentially contain more valuable information.

This thesis proposes a multi-layered HITS (Hyperlink-Induced Topic Search) algorithm to perform the ranking task on multi-sourced networks. Specifically, each node in the network receives an authority score and a hub score for evaluating the value of the node itself and the value of its outgoing links respectively. Based on a recent multi-layered network model, which allows more flexible dependency structure across different sources (i.e., layers), the proposed algorithm leverages both within-layer smoothness and cross-layer consistency. This essentially allows nodes from different layers to be ranked accordingly. The multi-layered HITS is formulated as a regularized optimization problem with non-negative constraint and solved by an iterative update process. Extensive experimental evaluations demonstrate the effectiveness and explainability of the proposed algorithm.