The history of AI has included several "waves" of ideas. The first wave, from the mid-1950s to the 1980s, focused on logic and symbolic hand-encoded representations of knowledge, the foundations of so-called "expert systems". The second wave, starting in the 1990s, focused on statistics and machine learning, in which, instead of hand-programming rules for behavior, programmers constructed "statistical learning algorithms" that could be trained on large datasets. In the most recent wave research in AI has largely focused on deep (i.e., many-layered) neural networks, which are loosely inspired by the brain and trained by "deep learning" methods. However, while deep neural networks have led to many successes and new capabilities in computer vision, speech recognition, language processing, game-playing, and robotics, their potential for broad application remains limited by several factors. A concerning limitation is that even the most successful of today's AI systems suffer from brittleness-they can fail in unexpected ways when faced with situations that differ sufficiently from ones they have been trained on. This lack of robustness also appears in the vulnerability of AI systems to adversarial attacks, in which an adversary can subtly manipulate data in a way to guarantee a specific wrong answer or action from an AI system. AI systems also can absorb biases-based on gender, race, or other factors-from their training data and further magnify these biases in their subsequent decision-making. Taken together, these various limitations have prevented AI systems such as automatic medical diagnosis or autonomous vehicles from being sufficiently trustworthy for wide deployment. The massive proliferation of AI across society will require radically new ideas to yield technology that will not sacrifice our productivity, our quality of life, or our values.

The use of computational simulation is by now so pervasive in society that it is no exaggeration to say that continued U.S. and international prosperity, security, and health depend in part on continued improvements in simulation capabilities. What if we could predict weather two weeks out, guide the design of new drugs for new viral diseases, or manage new manufacturing processes that cut production costs and times by an order of magnitude? What if we could predict collective human behavior, for example, response to an evacuation request during a natural disaster, or labor response to fiscal stimulus? (See also the companion CCC Quad Paper on Pandemic Informatics, which discusses features that would be essential to solving large-scale problems like preparation for, and response to, the inevitable next pandemic.) The past decade has brought remarkable advances in complementary areas: in sensors, which can now capture enormous amounts of data about the world, and in AI methods capable of learning to extract predictive patterns from those data. These advances may lead to a new era in computational simulation, in which sensors of many kinds are used to produce vast quantities of data, AI methods identify patterns in those data, and new AI-driven simulators combine machine-learned and mathematical rules to make accurate and actionable predictions. At the same time, there are new challenges -- computers in some important regards are no longer getting faster, and in some areas we are reaching the limits of mathematical understanding, or at least of our ability to translate mathematical understanding into efficient simulation. In this paper, we lay out some themes that we envision forming part of a cohesive, multi-disciplinary, and application-inspired research agenda on AI-driven simulators.

Neural network compression methods like pruning and quantization are very effective at efficiently deploying Deep Neural Networks (DNNs) on edge devices. However, DNNs remain vulnerable to adversarial examples-inconspicuous inputs that are specifically designed to fool these models. In particular, Universal Adversarial Perturbations (UAPs), are a powerful class of adversarial attacks which create adversarial perturbations that can generalize across a large set of inputs. In this work, we analyze the effect of various compression techniques to UAP attacks, including different forms of pruning and quantization. We test the robustness of compressed models to white-box and transfer attacks, comparing them with their uncompressed counterparts on CIFAR-10 and SVHN datasets. Our evaluations reveal clear differences between pruning methods, including Soft Filter and Post-training Pruning. We observe that UAP transfer attacks between pruned and full models are limited, suggesting that the systemic vulnerabilities across these models are different. This finding has practical implications as using different compression techniques can blunt the effectiveness of black-box transfer attacks. We show that, in some scenarios, quantization can produce gradient-masking, giving a false sense of security. Finally, our results suggest that conclusions about the robustness of compressed models to UAP attacks is application dependent, observing different phenomena in the two datasets used in our experiments.

Catastrophic forgetting refers to the tendency that a neural network "forgets" the previous learned knowledge upon learning new tasks. Prior methods have been focused on overcoming this problem on convolutional neural networks (CNNs), where the input samples like images lie in a grid domain, but have largely overlooked graph neural networks (GNNs) that handle non-grid data. In this paper, we propose a novel scheme dedicated to overcoming catastrophic forgetting problem and hence strengthen continual learning in GNNs. At the heart of our approach is a generic module, termed as topology-aware weight preserving~(TWP), applicable to arbitrary form of GNNs in a plug-and-play fashion. Unlike the main stream of CNN-based continual learning methods that rely on solely slowing down the updates of parameters important to the downstream task, TWP explicitly explores the local structures of the input graph, and attempts to stabilize the parameters playing pivotal roles in the topological aggregation. We evaluate TWP on different GNN backbones over several datasets, and demonstrate that it yields performances superior to the state of the art. Code is publicly available at \url{https://github.com/hhliu79/TWP}.

Our title alludes to the three Christmas ghosts encountered by Ebenezer Scrooge in \textit{A Christmas Carol}, who guide Ebenezer through the past, present, and future of Christmas holiday events. Similarly, our article will take readers through a journey of the past, present, and future of medical AI. In doing so, we focus on the crux of modern machine learning: the reliance on powerful but intrinsically opaque models. When applied to the healthcare domain, these models fail to meet the needs for transparency that their clinician and patient end-users require. We review the implications of this failure, and argue that opaque models (1) lack quality assurance, (2) fail to elicit trust, and (3) restrict physician-patient dialogue. We then discuss how upholding transparency in all aspects of model design and model validation can help ensure the reliability of medical AI.

Nowadays, heart disease is the leading cause of death worldwide. Predicting heart disease is a complex task since it requires experience along with advanced knowledge. Internet of Things (IoT) technology has lately been adopted in healthcare systems to collect sensor values for heart disease diagnosis and prediction. Many researchers have focused on the diagnosis of heart disease, yet the accuracy of the diagnosis results is low. To address this issue, an IoT framework is proposed to evaluate heart disease more accurately using a Modified Deep Convolutional Neural Network (MDCNN). The smartwatch and heart monitor device that is attached to the patient monitors the blood pressure and electrocardiogram (ECG). The MDCNN is utilized for classifying the received sensor data into normal and abnormal. The performance of the system is analyzed by comparing the proposed MDCNN with existing deep learning neural networks and logistic regression. The results demonstrate that the proposed MDCNN based heart disease prediction system performs better than other methods. The proposed method shows that for the maximum number of records, the MDCNN achieves an accuracy of 98.2 which is better than existing classifiers.

It is notoriously difficult to control the behavior of artificial neural networks such as generative neural language models. We recast the problem of controlling natural language generation as that of learning to interface with a pretrained language model, just as Application Programming Interfaces (APIs) control the behavior of programs by altering hyperparameters. In this new paradigm, a specialized neural network (called a Neural Programming Interface or NPI) learns to interface with a pretrained language model by manipulating the hidden activations of the pretrained model to produce desired outputs. Importantly, no permanent changes are made to the weights of the original model, allowing us to re-purpose pretrained models for new tasks without overwriting any aspect of the language model. We also contribute a new data set construction algorithm and GAN-inspired loss function that allows us to train NPI models to control outputs of autoregressive transformers. In experiments against other state-of-the-art approaches, we demonstrate the efficacy of our methods using OpenAI's GPT-2 model, successfully controlling noun selection, topic aversion, offensive speech filtering, and other aspects of language while largely maintaining the controlled model's fluency under deterministic settings.

3D multi-object tracking is an important component in robotic perception systems such as self-driving vehicles. Recent work follows a tracking-by-detection pipeline, which aims to match past tracklets with detections in the current frame. To avoid matching with false positive detections, prior work filters out detections with low confidence scores via a threshold. However, finding a proper threshold is non-trivial, which requires extensive manual search via ablation study. Also, this threshold is sensitive to many factors such as target object category so we need to re-search the threshold if these factors change. To ease this process, we propose to automatically select high-quality detections and remove the efforts needed for manual threshold search. Also, prior work often uses a single threshold per data sequence, which is sub-optimal in particular frames or for certain objects. Instead, we dynamically search threshold per frame or per object to further boost performance. Through experiments on KITTI and nuScenes, our method can filter out $45.7\%$ false positives while maintaining the recall, achieving new S.O.T.A. performance and removing the need for manually threshold tuning.

Achieving versatile robot locomotion requires motor skills which can adapt to previously unseen situations. We propose a Multi-Expert Learning Architecture (MELA) that learns to generate adaptive skills from a group of representative expert skills. During training, MELA is first initialised by a distinct set of pre-trained experts, each in a separate deep neural network (DNN). Then by learning the combination of these DNNs using a Gating Neural Network (GNN), MELA can acquire more specialised experts and transitional skills across various locomotion modes. During runtime, MELA constantly blends multiple DNNs and dynamically synthesises a new DNN to produce adaptive behaviours in response to changing situations. This approach leverages the advantages of trained expert skills and the fast online synthesis of adaptive policies to generate responsive motor skills during the changing tasks. Using a unified MELA framework, we demonstrated successful multi-skill locomotion on a real quadruped robot that performed coherent trotting, steering, and fall recovery autonomously, and showed the merit of multi-expert learning generating behaviours which can adapt to unseen scenarios.

These are the notes for the lectures that I was giving during Fall 2020 at the Moscow Institute of Physics and Technology (MIPT) and at the Yandex School of Data Analysis (YSDA). The notes cover some aspects of initialization, loss landscape, generalization, and a neural tangent kernel theory. While many other topics (e.g. expressivity, a mean-field theory, a double descent phenomenon) are missing in the current version, we plan to add them in future revisions.