The National Science Foundation has selected The University of Texas at Austin to lead the NSF AI Institute for Foundations of Machine Learning, bolstering the university's existing strengths in this emerging field. Machine learning is the technology that drives AI systems, enabling them to acquire knowledge and make predictions in complex environments. This technology has the potential to transform everything from transportation to entertainment to health care. UT Austin -- already among the world's top universities for artificial intelligence -- is poised to develop entirely new classes of algorithms that will lead to more sophisticated and beneficial AI technologies. The university will lead a larger team of researchers that includes the University of Washington, Wichita State University and Microsoft Research.

Discriminative learning based on convolutional neural networks (CNNs) aims to perform image restoration by learning from training examples of noisy-clean image pairs. It has become the go-to methodology for tackling image restoration and has outperformed the traditional non-local class of methods. However, the top-performing networks are generally composed of many convolutional layers and hundreds of neurons, with trainable parameters in excess of several millions. We claim that this is due to the inherent linear nature of convolution-based transformation, which is inadequate for handling severe restoration problems. Recently, a non-linear generalization of CNNs, called the operational neural networks (ONN), has been shown to outperform CNN on AWGN denoising. However, its formulation is burdened by a fixed collection of well-known nonlinear operators and an exhaustive search to find the best possible configuration for a given architecture, whose efficacy is further limited by a fixed output layer operator assignment. In this study, we leverage the Taylor series-based function approximation to propose a self-organizing variant of ONNs, Self-ONNs, for image restoration, which synthesizes novel nodal transformations onthe-fly as part of the learning process, thus eliminating the need for redundant training runs for operator search. In addition, it enables a finer level of operator heterogeneity by diversifying individual connections of the receptive fields and weights. We perform a series of extensive ablation experiments across three severe image restoration tasks. Even when a strict equivalence of learnable parameters is imposed, Self-ONNs surpass CNNs by a considerable margin across all problems, improving the generalization performance by up to 3 dB in terms of PSNR.

Deep learning's great success motivates many practitioners and students to learn about this exciting technology. However, it is often challenging for beginners to take their first step due to the complexity of understanding and applying deep learning. We present CNN Explainer, an interactive visualization tool designed for non-experts to learn and examine convolutional neural networks (CNNs), a foundational deep learning model architecture. Our tool addresses key challenges that novices face while learning about CNNs, which we identify from interviews with instructors and a survey with past students. CNN Explainer tightly integrates a model overview that summarizes a CNN's structure, and on-demand, dynamic visual explanation views that help users understand the underlying components of CNNs. Through smooth transitions across levels of abstraction, our tool enables users to inspect the interplay between low-level mathematical operations and high-level model structures. A qualitative user study shows that CNN Explainer helps users more easily understand the inner workings of CNNs, and is engaging and enjoyable to use. We also derive design lessons from our study. Developed using modern web technologies, CNN Explainer runs locally in users' web browsers without the need for installation or specialized hardware, broadening the public's education access to modern deep learning techniques.

The domain of Embodied AI, in which agents learn to complete tasks through interaction with their environment from egocentric observations, has experienced substantial growth with the advent of deep reinforcement learning and increased interest from the computer vision, NLP, and robotics communities. This growth has been facilitated by the creation of a large number of simulated environments (such as AI2-THOR, Habitat and CARLA), tasks (like point navigation, instruction following, and embodied question answering), and associated leaderboards. While this diversity has been beneficial and organic, it has also fragmented the community: a huge amount of effort is required to do something as simple as taking a model trained in one environment and testing it in another. This discourages good science. We introduce AllenAct, a modular and flexible learning framework designed with a focus on the unique requirements of Embodied AI research. AllenAct provides first-class support for a growing collection of embodied environments, tasks and algorithms, provides reproductions of state-of-the-art models and includes extensive documentation, tutorials, start-up code, and pre-trained models. We hope that our framework makes Embodied AI more accessible and encourages new researchers to join this exciting area. The framework can be accessed at: https://allenact.org/

The world has transitioned into a new phase of online learning in response to the recent Covid19 pandemic. Now more than ever, it has become paramount to push the limits of online learning in every manner to keep flourishing the education system. One crucial component of online learning is Knowledge Tracing (KT). The aim of KT is to model student's knowledge level based on their answers to a sequence of exercises referred as interactions. Students acquire their skills while solving exercises and each such interaction has a distinct impact on student ability to solve a future exercise. This \textit{impact} is characterized by 1) the relation between exercises involved in the interactions and 2) student forget behavior. Traditional studies on knowledge tracing do not explicitly model both the components jointly to estimate the impact of these interactions. In this paper, we propose a novel Relation-aware self-attention model for Knowledge Tracing (RKT). We introduce a relation-aware self-attention layer that incorporates the contextual information. This contextual information integrates both the exercise relation information through their textual content as well as student performance data and the forget behavior information through modeling an exponentially decaying kernel function. Extensive experiments on three real-world datasets, among which two new collections are released to the public, show that our model outperforms state-of-the-art knowledge tracing methods. Furthermore, the interpretable attention weights help visualize the relation between interactions and temporal patterns in the human learning process.

Markov decision processes (MDPs) are a fundamental mathematical abstraction for sequential decision making under uncertainty and they serve as a basic modeling tool in reinforcement learning (RL) and stochastic control [5, 24, 30]. Two prominent classes of MDPs are average-reward MDPs (AMDPs) and discounted MDPs (DMDPs). Each have been studied extensively; AMDPs are applicable to optimal control, learning automata, and various real-world reinforcement learning settings [17, 3, 22] and DMDPs have a number of nice theoretical properties including reward convergence and operator monotonicity [6]. In this paper we consider the prevalent computational learning problem of finding an approximately optimal policy of an MDP given only restricted access to the model. In particular, we consider the problem of computing an ɛ-optimal policy, i.e. a policy with an additive ɛ error in expected cumulative reward over infinite horizon, under the standard assumption of a generative model [14, 13], which allows one to sample from state-transitions given the current state-action pair. This problem is well-studied and there are multiple known upper and lower bounds on its sample complexity [4, 32, 28, 31]. In this work, we provide a unified framework based on primal-dual stochastic mirror descent (SMD) for learning an ɛ-optimal policies for both AMDPs and DMDPs with a generative model.

The theory and practice of stochastic optimization has focused on stochastic gradient descent (SGD) in recent years, retaining the basic first-order stochastic nature of SGD while aiming to improve it via mechanisms such as averaging, momentum, and variance reduction. Improvement can be measured along various dimensions, however, and it has proved difficult to achieve improvements both in terms of nonasymptotic measures of convergence rate and asymptotic measures of distributional tightness. In this work, we consider first-order stochastic optimization from a general statistical point of view, motivating a specific form of recursive averaging of past stochastic gradients. The resulting algorithm, which we refer to as \emph{Recursive One-Over-T SGD} (ROOT-SGD), matches the state-of-the-art convergence rate among online variance-reduced stochastic approximation methods. Moreover, under slightly stronger distributional assumptions, the rescaled last-iterate of ROOT-SGD converges to a zero-mean Gaussian distribution that achieves near-optimal covariance.

I recently started a new newsletter focus on AI education. TheSequence is a no-BS( meaning no hype, no news etc) AI-focused newsletter that takes 5 minutes to read. The goal is to keep you up to date with machine learning projects, research papers and concepts. Every once in a while, you encounter a research paper that is so simple and yet profound and brilliant that makes you wish you would have written it yourself. That's how I felt when I read François Chollet's On the Measure of Intelligence.

IMAGE: Scott Dodelson, professor and head of Carnegie Mellon University's Department of Physics, is the principal investigator of the AI Planning Institute on Physics of the Future. Carnegie Mellon University has received a $500,000 planning grant from the National Science Foundation (NSF) to work toward creating a National Artificial Intelligence Research Institute in Physics. Today, the NSF announced grants to create 5 full institutes and 10 planning institutes that will focus on advancing foundational artificial intelligence (AI) research, accelerating innovation in scientific fields using AI, building the next generation of talent and bringing together scientists from a wide range of fields for interdisciplinary collaboration. The grants represent the NSF's most significant investment in AI research and workforce development to-date. As a recipient of one of the planning institute grants, Carnegie Mellon will work over the next two years to develop the capacity to become a full institute.

Amazon has published videos and supplementary materials from several of its internal Machine Learning University courses. The course lectures cover three machine-learning topics and can be watched on-demand on YouTube, while the slides, notebooks, and datasets can be downloaded from GitHub. A total of twelve courses are planned to be released by the end of the year. Amazon announced the release of the courses in a recent blog post. The initial release consists of three "accelerated" courses, which all provide introductions to ML, then progress to the more specialized topics of tabular data, natural language processing (NLP), and computer vision (CV).