Deep learning has become a widely used tool for inference and prediction in neuroscience research. Despite their differences, most neural network architectures convert raw input data into lower-dimensional vector representations that subsequent network layers can more easily process. Significant advancements have been made in improving latent representations in audiovisual problems. However, human neurophysiological data is often scarcer, noisier, and more challenging to learn from when integrated from multiple sources. The present work integrates neural, physiological, and behavioral data to improve human behavior, preference, and state prediction. Across five studies, we explore (i) how embeddings, or vectorized representations, can be designed to understand the context of input data better, (ii) how the attention mechanism found in transformer models can be adapted to capture crossmodal relationships in an interpretable way, and (iii) how humans make sensorimotor decisions in a realistic scenario with implications for designing automated systems. Part I focuses on improving the context for latent representations in deep neural networks. We achieve this by introducing a hierarchical structure in clinical data to predict cognitive performance in a large, longitudinal cohort study. In a separate study, we present a recurrent neural network that captures non-cognitive pupil dynamics by utilizing visual areas of interest as inputs. In Part II, we employ attention-based approaches for multimodal integration by learning to weigh modalities that differ in the type of information they capture. We show that our crossmodal attention framework can adapt to audiovisual and neurophysiological input data. Part III proposes a novel paradigm to study sensorimotor decision-making in a driving scenario and study brain connectivity in the context of pupil-linked arousal. Our findings reveal that embeddings that capture input data's hierarchical or temporal context consistently yield high performance across different tasks. Moreover, our studies demonstrate the versatility of the attention mechanism, which we show can effectively integrate various modalities such as text descriptions, perceived differences in video clips, and recognized objects. Our multimodal transformer, designed to handle neurophysiological data, improves the prediction of emotional states by integrating brain and autonomic activity. Taken together, our work advances the development of multimodal systems for predicting human behavior, preference, and state across domains.

Ultrasound (US) is the most widely used medical imaging modality due to its low cost, portability, real time imaging ability and use of non-ionizing radiation. However, unlike other imaging modalities such as CT or MRI, it is a heavily operator dependent, requiring trained expertise to leverage these benefits. Recently there has been an explosion of interest in artificial intelligence (AI) across the medical community and many are turning to the growing trend of deep learning (DL) models to assist in diagnosis. However, deep learning models do not perform as well when training data is not fully representative of the problem. Due to this difference in training and deployment, model performance suffers which can lead to misdiagnosis. This issue is known as dataset shift. Two aims to address dataset shift were proposed. The first was to quantify how US operator skill and hardware affects acquired images. The second was to use this skill quantification method to screen and match data to deep learning models to improve performance. A BLUE phantom from CAE Healthcare (Sarasota, FL) with various mock lesions was scanned by three operators using three different US systems (Siemens S3000, Clarius L15, and Ultrasonix SonixTouch) producing 39013 images. DL models were trained on a specific set to classify the presence of a simulated tumour and tested with data from differing sets. The Xception, VGG19, and ResNet50 architectures were used to test the effects with varying frameworks. K-Means clustering was used to separate images generated by operator and hardware into clusters. This clustering algorithm was then used to screen incoming images during deployment to best match input to an appropriate DL model which is trained specifically to classify that type of operator or hardware. Results showed a noticeable difference when models were given data from differing datasets with the largest accuracy drop being 81.26% to 31.26%. Overall, operator differences more significantly affected DL model performance. Clustering models had much higher success separating hardware data compared to operator data. The proposed method reflects this result with a much higher accuracy across the hardware test set compared to the operator data. / Thesis / Master of Applied Science (MASc)

The past decade has seen tremendous growth in potential applications of language technologies in our daily lives due to increasing data, computational resources, and user interfaces. An important step to support emerging applications is the development of algorithms for processing the rich variety of human-generated text and extracting relevant information. Machine learning, especially deep learning, has seen increasing success on various text benchmarks. However, while standard benchmarks have static tasks with expensive human-labeled data, real-world applications are characterized by dynamic task specifications and limited resources for data labeling, thus making it challenging to transfer the success of supervised machine learning to the real world. To deploy language technologies at scale, it is crucial to develop alternative techniques for teaching machines beyond data labeling. In this dissertation, we address this data labeling bottleneck by studying and presenting resource-efficient frameworks for teaching machine learning models to solve language tasks across diverse domains and languages. Our goal is to (i) support emerging real-world problems without the expensive requirement of large-scale manual data labeling; and (ii) assist humans in teaching machines via more flexible types of interaction. Towards this goal, we describe our collaborations with experts across domains (including public health, earth sciences, news, and e-commerce) to integrate weakly-supervised neural networks into operational systems, and we present efficient machine teaching frameworks that leverage flexible forms of declarative knowledge as supervision: coarse labels, large hierarchical taxonomies, seed words, bilingual word translations, and general labeling rules. First, we present two neural network architectures that we designed to leverage weak supervision in the form of coarse labels and hierarchical taxonomies, respectively, and highlight their successful integration into operational systems. Our Hierarchical Sigmoid Attention Network (HSAN) learns to highlight important sentences of potentially long documents without sentence-level supervision by, instead, using coarse-grained supervision at the document level. HSAN improves over previous weakly supervised learning approaches across sentiment classification benchmarks and has been deployed to help inspections in health departments for the discovery of foodborne illness outbreaks. We also present TXtract, a neural network that extracts attributes for e-commerce products from thousands of diverse categories without using manually labeled data for each category, by instead considering category relationships in a hierarchical taxonomy. TXtract is a core component of Amazon’s AutoKnow, a system that collects knowledge facts for over 10K product categories, and serves such information to Amazon search and product detail pages. Second, we present architecture-agnostic machine teaching frameworks that we applied across domains, languages, and tasks. Our weakly-supervised co-training framework can train any type of text classifier using just a small number of class-indicative seed words and unlabeled data. In contrast to previous work that use seed words to initialize embedding layers, our iterative seed word distillation (ISWD) method leverages the predictive power of seed words as supervision signals and shows strong performance improvements for aspect detection in reviews across domains and languages. We further demonstrate the cross-lingual transfer abilities of our co-training approach via cross-lingual teacher-student (CLTS), a method for training document classifiers across diverse languages using labeled documents only in English and a limited budget for bilingual translations. Not all classification tasks, however, can be effectively addressed using human supervision in the form of seed words. To capture a broader variety of tasks, we present weakly-supervised self-training (ASTRA), a weakly-supervised learning framework for training a classifier using more general labeling rules in addition to labeled and unlabeled data. As a complete set of accurate rules may be hard to obtain all in one shot, we further present an interactive framework that assists human annotators by automatically suggesting candidate labeling rules. In conclusion, this thesis demonstrates the benefits of teaching machines with different types of interaction than the standard data labeling paradigm and shows promising results for new applications across domains and languages. To facilitate future research, we publish our code implementations and design new challenging benchmarks with various types of supervision. We believe that our proposed frameworks and experimental findings will influence research and will enable new applications of language technologies without the costly requirement of large manually labeled datasets.

Machine learning techniques promise to greatly accelerate structural design and optimization. In this thesis, deep learning and active learning techniques are applied to different non-convex structural optimization problems. Finite Element Analysis (FEA) based standard optimization methods for aircraft panels with bio-inspired curvilinear stiffeners are computationally expensive. The main reason for employing many of these standard optimization methods is the ease of their integration with FEA. However, each optimization requires multiple computationally expensive FEA evaluations, making their use impractical at times. To accelerate optimization, the use of Deep Neural Networks (DNNs) is proposed to approximate the FEA buckling response. The results show that DNNs obtained an accuracy of 95% for evaluating the buckling load. The DNN accelerated the optimization by a factor of nearly 200. The presented work demonstrates the potential of DNN-based machine learning algorithms for accelerating the optimization of bio-inspired curvilinearly stiffened panels. But, the approach could have disadvantages for being only specific to similar structural design problems, and requiring large datasets for DNNs training. An adaptive machine learning technique called active learning is used in this thesis to accelerate the evolutionary optimization of complex structures. The active learner helps the Genetic Algorithms (GA) by predicting if the possible design is going to satisfy the required constraints or not. The approach does not need a trained surrogate model prior to the optimization. The active learner adaptively improve its own accuracy during the optimization for saving the required number of FEA evaluations. The results show that the approach has the potential to reduce the total required FEA evaluations by more than 50%. Lastly, the machine learning is used to make recommendations for modeling choices while analyzing a structure using FEA. The decisions about the selection of appropriate modeling techniques are usually based on an analyst's judgement based upon their knowledge and intuition from past experience. The machine learning-based approach provides recommendations within seconds, thus, saving significant computational resources for making accurate design choices. / Doctor of Philosophy / This thesis presents an innovative application of artificial intelligence (AI) techniques for designing aircraft structures. An important objective for the aerospace industry is to design robust and fuel-efficient aerospace structures. The state of the art research in the literature shows that the structure of aircraft in future could mimic organic cellular structure. However, the design of these new panels with arbitrary structures is computationally expensive. For instance, applying standard optimization methods currently being applied to aerospace structures to design an aircraft, can take anywhere from a few days to months. The presented research demonstrates the potential of AI for accelerating the optimization of an aircraft structures. This will provide an efficient way for aircraft designers to design futuristic fuel-efficient aircraft which will have positive impact on the environment and the world.

Recent advances in deep learning models have shown impressive capabilities in various computer vision tasks, which encourages the integration of these models into real-world vision systems such as smart devices. This integration presents new challenges as models need to meet complex real-world requirements. This thesis is dedicated to building practical deep learning models, where we focus on two main challenges in vision systems: data efficiency and variability. We address these issues by providing a general model adaptation framework that extends models with practical capabilities. In the first part of the thesis, we explore model adaptation approaches for efficient representation. We illustrate the benefits of different types of efficient data representations, including compressed video modalities from video codecs, low-bit features and sparsified frames and texts. By using such efficient representation, the system complexity such as data storage, processing and computation can be greatly reduced. We systematically study various methods to extract, learn and utilize these representations, presenting new methods to adapt machine learning models for them. The proposed methods include a compressed-domain video recognition model with coarse-to-fine distillation training strategy, a task-specific feature compression framework for low-bit video-and-language understanding, and a learnable token sparsification approach for sparsifying human-interpretable video inputs. We demonstrate new perspectives of representing vision data in a more practical and efficient way in various applications. The second part of the thesis focuses on open environment challenges, where we explore model adaptation for new, unseen classes and domains. We examine the practical limitations in current recognition models, and introduce various methods to empower models in addressing open recognition scenarios. This includes a negative envisioning framework for managing new classes and outliers, and a multi-domain translation approach for dealing with unseen domain data. Our study shows a promising trajectory towards models exhibiting the capability to navigate through diverse data environments in real-world applications.

This thesis consists of studies of two important problems in transfer learning: binary classification under covariate-shift transfer, and off-policy evaluation in reinforcement learning. First, the problem of binary classification under covariate shift is considered, for which the first efficient procedure for optimal pruning of a dyadic classification tree is presented, where optimality is derived with respect to a notion of 𝒂𝒗𝒆𝒓𝒂𝒈𝒆 𝒅𝒊𝒔𝒄𝒓𝒆𝒑𝒂𝒏𝒄𝒚 between the shifted marginal distributions of source and target. Further, it is demonstrated that the procedure is adaptive to the discrepancy between marginal distributions in a neighbourhood of the decision boundary. It is shown how this notion of average discrepancy can be viewed as a measure of 𝒓𝒆𝒍𝒂𝒕𝒊𝒗𝒆 𝒅𝒊𝒎𝒆𝒏𝒔𝒊𝒐𝒏 between distributions, as it relates to existing notions of information such as the Minkowski and Renyi dimensions. Experiments are carried out on real data to verify the efficacy of the pruning procedure as compared to other baseline methods for pruning under transfer. The problem of off-policy evaluation for reinforcement learning is then considered, where two minimax lower bounds for the mean-square error of off-policy evaluation under Markov decision processes are derived. The first of these gives a non-asymptotic lower bound for OPE in finite state and action spaces over a model in which the mean reward is perturbed arbitrarily (up to a given magnitude) that depends on an average weighted chi-square divergence between the behaviour and target policies. The second provides an asymptotic lower bound for OPE in continuous state-space when the mean reward and policy ratio functions lie in a certain smoothness class. Finally, the results of a study that purported to have derived a policy for sepsis treatment in ICUs are replicated and shown to suffer from excessive variance and therefore to be unreliable; our lower bound is computed and used as evidence that reliable off-policy estimation from this data would have required a great deal more samples than were available.

Machine learning models, typically deep learning models, often come at the cost of explainability. To generate explanations of such systems, models need to be rooted in first-principles, at least mechanistically. In this work we look at a gamete of machine learning models based on different levels of process knowledge for process fault diagnosis and generating mechanistic explanations of processes. In chapter 1, we introduce the thesis using a range of problems from causality, explainability, aiming towards the goal of generating mechanistic explanations of process systems. Chapter 2 looks at an approach for generating causal models purely through data-centric approach, with minimal process knowledge with respect to equipment connectivity and identifying causality in the domains. These causal models generated can be utilized for process fault diagnosis. Chapter 3 and chapter 4 show how deep learning models can be used for both classification for process fault diagnosis and regression. We see that depending on the hyperparameters, i.e., purely the breadth and depth of a neural network, the learned hidden representations vary from a simple set of features, to more complex sets of features. While these hidden representations may be exploited to aid in classification and regression problems, the true explanations of these representations do not correlate with mechanisms in the system of interest. There is thus a requirement to add more mechanistic information about the features generated to aid in explainability. Chapter 5 shows how incorporating process knowledge can aid in generating such mechanistic explanations based on automated variable transformations. In this chapter we show how process knowledge can be used to generate features, or model forms to generate explainable models. These models have the ability of extracting the true models of the system from the model knowledge provided.

Anwendung von maschinellen Lernverfahren (ML) in der Produktionstechnik, in Zeiten der Industrie 4.0, stark angestiegen. Insbesondere die Datenverfügbarkeit ist an dieser Stelle elementar und für die erfolgreiche Umsetzung einer ML-Applikation Voraussetzung. Falls für eine gegebene Problemstellung die Datenmenge oder -qualität nicht ausreichend ist, können Techniken, wie die Datenaugmentierung, der Einsatz von synthetischen Daten sowie das Transferlernen von ähnlichen Datensätzen Abhilfe schaffen. Innerhalb dieser Ausarbeitung wird das Konzept des Transferlernens im Bereich das Radial-Axial Ringwalzens (RAW) angewendet und am Beispiel der Zeitreihenprognose des Außendurchmessers über die Prozesszeit durchgeführt. Das Radial-Axial Ringwalzen ist ein warmumformendes Verfahren und dient der nahtlosen Ringherstellung.

Due to the increasing computing power and corresponding algorithms, the use of machine learning (ML) in production technology has risen sharply in the age of Industry 4.0. Data availability in particular is fundamental at this point and a prerequisite for the successful implementation of a ML application. If the quantity or quality of data is insufficient for a given problem, techniques such as data augmentation, the use of synthetic data and transfer learning of similar data sets can provide a remedy. In this paper, the concept of transfer learning is applied in the field of radial-axial ring rolling (rarr) and implemented using the example of time series prediction of the outer diameter over the process time. Radial-axial ring rolling is a hot forming process and is used for seamless ring production.

Deep learning has seen rapid evolution in the past decade, accomplishing tasks that were previously unimaginable. At the same time, researchers strive to better understand and interpret the underlying mechanisms of the deep models, which are often justifiably regarded as "black boxes". Overcoming this deficiency will not only serve to suggest better learning architectures and training methods, but also extend deep learning to scenarios where interpretability is key to the application. One such scenario is signal detection and estimation, with gravitational wave detection as a specific example, where classic methods are often preferred for their interpretability. Nonetheless, while classic statistical detection methods such as matched filtering excel in their simplicity and intuitiveness, they can be suboptimal in terms of both accuracy and computational efficiency. Therefore, it is appealing to have methods that achieve ``the best of both worlds'', namely enjoying simultaneously excellent performance and interpretability. In this thesis, we aim to bridge this gap between modern deep learning and classic statistical detection, by revisiting the signal detection problem from a new perspective. First, to address the perceived distinction in interpretability between classic matched filtering and deep learning, we state the intrinsic connections between the two families of methods, and identify how trainable networks can address the structural limitations of matched filtering. Based on these ideas, we propose two trainable architectures that are constructed based on matched filtering, but with learnable templates and adaptivity to unknown noise distributions, and therefore higher detection accuracy. We next turn our attention toward improving the computational efficiency of detection, where we aim to design architectures that leverage structures within the problem for efficiency gains. By leveraging the statistical structure of class imbalance, we integrate hierarchical detection into trainable networks, and use a novel loss function which explicitly encodes both detection accuracy and efficiency. Furthermore, by leveraging the geometric structure of the signal set, we consider using signal space optimization as an alternative computational primitive for detection, which is intuitively more efficient than covering with a template bank. We theoretical prove the efficiency gain by analyzing Riemannian gradient descent on the signal manifold, which reveals an exponential improvement in efficiency over matched filtering. We also propose a practical trainable architecture for template optimization, which makes use of signal embedding and kernel interpolation. We demonstrate the performance of all proposed architectures on the task of gravitational wave detection in astrophysics, where matched filtering is the current method of choice. The architectures are also widely applicable to general signal or pattern detection tasks, which we exemplify with the handwritten digit recognition task using the template optimization architecture. Together, we hope the this work useful to scientists and engineers seeking machine learning architectures with high performance and interpretability, and contribute to our understanding of deep learning as a whole.