We consider the problem of OOD generalization, where the goal is to train a model that performs well on test distributions that are different from the training distribution. Deep learning models are known to be fragile to such shifts and can suffer large accuracy drops even for slightly different test distributions. We propose a new method - DAFT - based on the intuition that adversarially robust combination of a large number of rich features should provide OOD robustness. Our method carefully distills the knowledge from a powerful teacher that learns several discriminative features using standard training while combining them using adversarial training. The standard adversarial training procedure is modified to produce teachers which can guide the student better. We evaluate DAFT on standard benchmarks in the DomainBed framework, and demonstrate that DAFT achieves significant improvements over the current state-of-the-art OOD generalization methods. DAFT consistently out-performs well-tuned ERM and distillation baselines by up to 6%, with more pronounced gains for smaller networks.

Prediction over event sequences is critical for many real-world applications in Information Retrieval and Natural Language Processing. Future Event Generation (FEG) is a challenging task in event sequence prediction because it requires not only fluent text generation but also commonsense reasoning to maintain the logical coherence of the entire event story. In this paper, we propose a novel explainable FEG framework, Coep. It highlights and integrates two types of event knowledge, sequential knowledge of direct event-event relations and inferential knowledge that reflects the intermediate character psychology between events, such as intents, causes, reactions, which intrinsically pushes the story forward. To alleviate the knowledge forgetting issue, we design two modules, Im and Gm, for each type of knowledge, which are combined via prompt tuning. First, Im focuses on understanding inferential knowledge to generate commonsense explanations and provide a soft prompt vector for Gm. We also design a contrastive discriminator for better generalization ability. Second, Gm generates future events by modeling direct sequential knowledge with the guidance of Im. Automatic and human evaluation demonstrate that our approach can generate more coherent, specific, and logical future events.

Robots will experience non-stationary environment dynamics throughout their lifetime: the robot dynamics can change due to wear and tear, or its surroundings may change over time. Eventually, the robots should perform well in all of the environment variations it has encountered. At the same time, it should still be able to learn fast in a new environment. We identify two challenges in Reinforcement Learning (RL) under such a lifelong learning setting with off-policy data: first, existing off-policy algorithms struggle with the trade-off between being conservative to maintain good performance in the old environment and learning efficiently in the new environment, despite keeping all the data in the replay buffer. We propose the Offline Distillation Pipeline to break this trade-off by separating the training procedure into an online interaction phase and an offline distillation phase.Second, we find that training with the imbalanced off-policy data from multiple environments across the lifetime creates a significant performance drop. We identify that this performance drop is caused by the combination of the imbalanced quality and size among the datasets which exacerbate the extrapolation error of the Q-function. During the distillation phase, we apply a simple fix to the issue by keeping the policy closer to the behavior policy that generated the data. In the experiments, we demonstrate these two challenges and the proposed solutions with a simulated bipedal robot walk-ing task across various environment changes. We show that the Offline Distillation Pipeline achieves better performance across all the encountered environments without affecting data collection. We also provide a comprehensive empirical study to support our hypothesis on the data imbalance issue.

Recently, the attention-enhanced multi-layer encoder, such as Transformer, has been extensively studied in Machine Reading Comprehension (MRC). To predict the answer, it is common practice to employ a predictor to draw information only from the final encoder layer which generates the coarse-grained representations of the source sequences, i.e., passage and question. The analysis shows that the representation of source sequence becomes more coarse-grained from finegrained as the encoding layer increases. It is generally believed that with the growing number of layers in deep neural networks, the encoding process will gather relevant information for each location increasingly, resulting in more coarse-grained representations, which adds the likelihood of similarity to other locations (referring to homogeneity). Such phenomenon will mislead the model to make wrong judgement and degrade the performance. In this paper, we argue that it would be better if the predictor could exploit representations of different granularity from the encoder, providing different views of the source sequences, such that the expressive power of the model could be fully utilized. To this end, we propose a novel approach called Adaptive Bidirectional Attention-Capsule Network (ABA-Net), which adaptively exploits the source representations of different levels to the predictor. Furthermore, due to the better representations are at the core for boosting MRC performance, the capsule network and self-attention module are carefully designed as the building blocks of our encoders, which provides the capability to explore the local and global representations, respectively. Experimental results on three benchmark datasets, i.e., SQuAD 1.0, SQuAD 2.0 and COQA, demonstrate the effectiveness of our approach. In particular, we set the new state-of-the-art performance on the SQuAD 1.0 dataset

Although many near-Earth objects have been found by ground-based telescopes, some fast-moving ones, especially those near detection limits, have been missed by observatories. We developed a convolutional neural network for detecting faint fast-moving near-Earth objects. It was trained with artificial streaks generated from simulations and was able to find these asteroid streaks with an accuracy of 98.7% and a false positive rate of 0.02% on simulated data. This program was used to search image data from the Zwicky Transient Facility (ZTF) in four nights in 2019, and it identified six previously undiscovered asteroids. The visual magnitudes of our detections range from ~19.0 - 20.3 and motion rates range from ~6.8 - 24 deg/day, which is very faint compared to other ZTF detections moving at similar motion rates. Our asteroids are also ~1 - 51 m diameter in size and ~5 - 60 lunar distances away at close approach, assuming their albedo values follow the albedo distribution function of known asteroids. The use of a purely simulated dataset to train our model enables the program to gain sensitivity in detecting faint and fast-moving objects while still being able to recover nearly all discoveries made by previously designed neural networks which used real detections to train neural networks. Our approach can be adopted by any observatory for detecting fast-moving asteroid streaks.

Online reinforcement learning (RL) algorithms are increasingly used to personalize digital interventions in the fields of mobile health and online education. Common challenges in designing and testing an RL algorithm in these settings include ensuring the RL algorithm can learn and run stably under real-time constraints, and accounting for the complexity of the environment, e.g., a lack of accurate mechanistic models for the user dynamics. To guide how one can tackle these challenges, we extend the PCS (Predictability, Computability, Stability) framework, a data science framework that incorporates best practices from machine learning and statistics in supervised learning (Yu and Kumbier, 2020), to the design of RL algorithms for the digital interventions setting. Further, we provide guidelines on how to design simulation environments, a crucial tool for evaluating RL candidate algorithms using the PCS framework. We illustrate the use of the PCS framework for designing an RL algorithm for Oralytics, a mobile health study aiming to improve users' tooth-brushing behaviors through the personalized delivery of intervention messages. Oralytics will go into the field in late 2022.

In present time, the information technology is playing a crucial role in every sector and various advancements are being introduced with every passing day thereby resolving several issues and making work easy for the people. Moreover, with every minute, the technology is upgrading and several new inventions are making place in life. One such thing is Artificial Intelligence, which is not fast emerging and being introduced in every sector. Moreover, looking at the increasing demand and utility of the same in the coming time, the Government is also taking steps for making it in reach of every student, right from the beginning level, giving it a special place in the National Education Policy 2020, which is being implemented across the country. Although the policy, formulated in 2020, got delayed for two years due to COVID pandemic across country but, now, when the situation has improved significantly, efforts are on ensure its implementation across the nation. As per experts, the new education policy will totally transform the existing education system which is aimed for producing clerks to do white-collar jobs, but the New Education Policy has been devised with such an approach, which is aimed at the holistic development of students, that too as per the latest requirements and demands, so that they can transform into responsible citizens of country.

Machine learning (ML) is a type of artificial intelligence (AI) that allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so. Machine learning algorithms use historical data as input to predict new output values.

Deep Learning is the subset of Machine Learning that primarily deals with Neural Networks. Deep Learning skills are the key skills that students today need to be able to thrive in the global economy. Deep learning skills can help them land prestigious job positions at FAANG companies. FAANG is an acronym that indicates the stocks of five prominent American technology companies: Facebook, Amazon, Apple, Netflix, and Google. Read on to find out more about the key deep learning skills in demand for FAANG.

Take a deeper dive into machine learning with Amazon Web Services (AWS). In this practical course, instructor Jonathan Fernandes helps to familiarize you with common machine learning tasks, demonstrating how to approach each one using key techniques: binary classification, multiclass classification, and regression. Throughout the course, he walks through several examples, using Kaggle datasets for hands-on exploration. Plus, he reviews some essential machine learning concepts and helps to familiarize you with other AWS capabilities, including SageMaker and Deep Learning AMIs.