Digitization is penetrating more and more areas of life. Tasks are increasingly being completed digitally, and are therefore not only fulfilled faster, more efficiently but also more purposefully and successfully. The rapid developments in the field of artificial intelligence in recent years have played a major role in this, as they brought up many helpful approaches to build on. At the same time, the eyes, their movements, and the meaning of these movements are being progressively researched. The combination of these developments has led to exciting approaches. In this dissertation, I present some of these approaches which I worked on during my Ph.D. First, I provide insight into the development of models that use artificial intelligence to connect eye movements with visual expertise. This is demonstrated for two domains or rather groups of people: athletes in decision-making actions and surgeons in arthroscopic procedures. The resulting models can be considered as digital diagnostic models for automatic expertise recognition. Furthermore, I show approaches that investigate the transferability of eye movement patterns to different expertise domains and subsequently, important aspects of techniques for generalization. Finally, I address the temporal detection of confusion based on eye movement data. The results suggest the use of the resulting model as a clock signal for possible digital assistance options in the training of young professionals. An interesting aspect of my research is that I was able to draw on very valuable data from DFB youth elite athletes as well as on long-standing experts in arthroscopy. In particular, the work with the DFB data attracted the interest of radio and print media, namely DeutschlandFunk Nova and SWR DasDing. All resulting articles presented here have been published in internationally renowned journals or at conferences.

We propose a new policy parameterization for representing 3D rotations during reinforcement learning. Today in the continuous control reinforcement learning literature, many stochastic policy parameterizations are Gaussian. We argue that universally applying a Gaussian policy parameterization is not always desirable for all environments. One such case in particular where this is true are tasks that involve predicting a 3D rotation output, either in isolation, or coupled with translation as part of a full 6D pose output. Our proposed Bingham Policy Parameterization (BPP) models the Bingham distribution and allows for better rotation (quaternion) prediction over a Gaussian policy parameterization in a range of reinforcement learning tasks. We evaluate BPP on the rotation Wahba problem task, as well as a set of vision-based next-best pose robot manipulation tasks from RLBench. We hope that this paper encourages more research into developing other policy parameterization that are more suited for particular environments, rather than always assuming Gaussian.

A knowledge graph (KG) consists of a set of interconnected typed entities and their attributes. Recently, KGs are popularly used as the auxiliary information to enable more accurate, explainable, and diverse user preference recommendations. Specifically, existing KG-based recommendation methods target modeling high-order relations/dependencies from long connectivity user-item interactions hidden in KG. However, most of them ignore the cold-start problems (i.e., user cold-start and item cold-start) of recommendation analytics, which restricts their performance in scenarios when involving new users or new items. Inspired by the success of meta-learning on scarce training samples, we propose a novel meta-learning based framework called MetaKG, which encompasses a collaborative-aware meta learner and a knowledge-aware meta learner, to capture meta users' preference and entities' knowledge for cold-start recommendations. The collaborative-aware meta learner aims to locally aggregate user preferences for each user preference learning task. In contrast, the knowledge-aware meta learner is to globally generalize knowledge representation across different user preference learning tasks. Guided by two meta learners, MetaKG can effectively capture the high-order collaborative relations and semantic representations, which could be easily adapted to cold-start scenarios. Besides, we devise a novel adaptive task scheduler which can adaptively select the informative tasks for meta learning in order to prevent the model from being corrupted by noisy tasks. Extensive experiments on various cold-start scenarios using three real data sets demonstrate that our presented MetaKG outperforms all the existing state-of-the-art competitors in terms of effectiveness, efficiency, and scalability.

Visual classification can be divided into coarse-grained and fine-grained classification. Coarse-grained classification represents categories with a large degree of dissimilarity, such as the classification of cats and dogs, while fine-grained classification represents classifications with a large degree of similarity, such as cat species, bird species, and the makes or models of vehicles. Unlike coarse-grained visual classification, fine-grained visual classification often requires professional experts to label data, which makes data more expensive. To meet this challenge, many approaches propose to automatically find the most discriminative regions and use local features to provide more precise features. These approaches only require image-level annotations, thereby reducing the cost of annotation. However, most of these methods require two- or multi-stage architectures and cannot be trained end-to-end. Therefore, we propose a novel plug-in module that can be integrated to many common backbones, including CNN-based or Transformer-based networks to provide strongly discriminative regions. The plugin module can output pixel-level feature maps and fuse filtered features to enhance fine-grained visual classification. Experimental results show that the proposed plugin module outperforms state-of-the-art approaches and significantly improves the accuracy to 92.77\% and 92.83\% on CUB200-2011 and NABirds, respectively. We have released our source code in Github https://github.com/chou141253/FGVC-PIM.git.

Learning representations of multimodal data that are both informative and robust to missing modalities at test time remains a challenging problem due to the inherent heterogeneity of data obtained from different channels. To address it, we present a novel Geometric Multimodal Contrastive (GMC) representation learning method comprised of two main components: i) a two-level architecture consisting of modality-specific base encoder, allowing to process an arbitrary number of modalities to an intermediate representation of fixed dimensionality, and a shared projection head, mapping the intermediate representations to a latent representation space; ii) a multimodal contrastive loss function that encourages the geometric alignment of the learned representations. We experimentally demonstrate that GMC representations are semantically rich and achieve state-of-the-art performance with missing modality information on three different learning problems including prediction and reinforcement learning tasks.

Online learning via Bayes' theorem allows new data to be continuously integrated into an agent's current beliefs. However, a naive application of Bayesian methods in non stationary environments leads to slow adaptation and results in state estimates that may converge confidently to the wrong parameter value. A common solution when learning in changing environments is to discard/downweight past data; however, this simple mechanism of "forgetting" fails to account for the fact that many real-world environments involve revisiting similar states. We propose a new framework, Bayes with Adaptive Memory (BAM), that takes advantage of past experience by allowing the agent to choose which past observations to remember and which to forget. We demonstrate that BAM generalizes many popular Bayesian update rules for non-stationary environments. Through a variety of experiments, we demonstrate the ability of BAM to continuously adapt in an ever-changing world.

Center for Artificial Intelligence at IIIT-Delhi and Artificial Intelligence Institute, University of South Carolina sign MoU Center for Artificial Intelligence (CAI), Indraprastha Institute of Information Technology Delhi (IIIT-Delhi), and Artificial Intelligence Institute, University of South Carolina (AIISC) recently signed an MoU to promote a close association between the Institutes through academic cooperation and research collaboration, with an international focus among students and faculty members, for the mutual benefit of both parties. This new connection between the institutions will facilitate the sharing of co-advised thesis or participating on the dissertation committee for students & PhD candidates and the interchange of scholarly papers, research materials, and other information in both parties' areas of interest. This cooperation involves collaborative research and activities and strong internship chances at AIISC for IIIT-Delhi students. The MoU further specifies that the parties can develop specific joint educational programmes in the future and enjoy the benefits of interchange of research, teaching, and technical personnel. The Center for Artificial Intelligence (CAI), IIIT-Delhi and AIISC have many knowledge and skills from world-class academic experts to students.

What do we need to do to increase the data literacy of our organization? In a world where your personal data, and the preferences and biases buried in that data, are being used to influence your behaviors, beliefs, and decisions, data literacy becomes an indispensable fundamental skill. And it's not just corporations that need this training. Data Literacy should be taught in universities, in high schools, in middle schools and even in adult education and nursing homes. Data literacy training needs to educate EVERYONE into how their personal data is being collected, analyzed, and used, so as to not be duped into actions, behaviors, and beliefs by organizations and people who understand how to manipulate your personal data to their benefit.

For a subscription service business, there are two ways to drive growth: grow the number of new customers, or increase the lifetime value from the customers that you already have by retaining more of them. Improving customer retention requires the ability to predict which subscribers are likely to cancel (referred to as churn), and to intervene with the right retention offers at the right time. Recently, the use of deep learning algorithms that learn sequential product usage customer behavior to make predictions have begun to offer businesses a more powerful method to pinpoint accounts at risk. This understanding of an account's churn likelihood allows a company to proactively act to save the most valuable customers before they cancel. CSE recently partnered with the finance group of Majid Al Futtaim Ventures (MAF), a leading mall, communities, retail and leisure pioneer across the Middle East, Africa and Asia, to design and deploy a machine learning solution to predict attrition within their consumer credit card customer base. MAF sought to use their customer records – including transaction and incident history plus account profile information – to inform a predictive model.

In the beginning website, design developers and designers designed websites using HTML. Soon, the internet was formless and empty, darkness was over the surface of the deep web, and the Spirit of Code was hovering over the pinnacle of utmost ignorance. We've come a long way from that time. The internet is still a dark, dreadful place, but it's much more stylish, sophisticated, and amazing now. Website Design has grown exponentially in scale and sophistication over the last few years, thanks to new Artificial Intelligence-based website creation tools that are dominating the digital marketing industry.