Recent work has constructed neural networks that are equivariant to continuous symmetry groups such as 2D and 3D rotations. This is accomplished using explicit group representations to derive the equivariant kernels and nonlinearities. We present two contributions motivated by frontier applications of equivariance beyond rotations and translations. First, we relax the requirement for explicit Lie group representations, presenting a novel algorithm that finds irreducible representations of noncommutative Lie groups given only the structure constants of the associated Lie algebra. Second, we demonstrate that Lorentz-equivariance is a useful prior for object-tracking tasks and construct the first object-tracking model equivariant to the Poincar\'e group.

In model-based learning, an agent's model is commonly defined over transitions between consecutive states of an environment even though planning often requires reasoning over multi-step timescales, with intermediate states either unnecessary, or worse, accumulating prediction error. In contrast, intelligent behaviour in biological organisms is characterised by the ability to plan over varying temporal scales depending on the context. Inspired by the recent works on human time perception, we devise a novel approach to learning a transition dynamics model, based on the sequences of episodic memories that define the agent's subjective timescale - over which it learns world dynamics and over which future planning is performed. We implement this in the framework of active inference and demonstrate that the resulting subjective-timescale model (STM) can systematically vary the temporal extent of its predictions while preserving the same computational efficiency. Additionally, we show that STM predictions are more likely to introduce future salient events (for example new objects coming into view), incentivising exploration of new areas of the environment. As a result, STM produces more informative action-conditioned roll-outs that assist the agent in making better decisions. We validate significant improvement in our STM agent's performance in the Animal-AI environment against a baseline system, trained using the environment's objective-timescale dynamics. An agent endowed with a model of its environment has the ability to predict the consequences of its actions and perform planning into the future before deciding on its next move. Models can allow agents to simulate the possible action-conditioned futures from their current state, even if the state was never visited during learning. As a result, model-based approaches can provide agents with better generalization abilities across both states and tasks in an environment, compared to their model-free counterparts (Racanière et al., 2017; Mishra et al., 2017).

Analysis of a large amount of data has always brought value to institutions and organizations. Lately, people's opinions expressed through text have become a very important aspect of this analysis. In response to this challenge, a natural language processing technique known as Aspect-Based Sentiment Analysis (ABSA) has emerged. Having the ability to extract the polarity for each aspect of opinions separately, ABSA has found itself useful in a wide range of domains. Education is one of the domains in which ABSA can be successfully utilized. Being able to understand and find out what students like and don't like most about a course, professor, or teaching methodology can be of great importance for the respective institutions. While this task represents a unique NLP challenge, many studies have proposed different approaches to tackle the problem. In this work, we present a comprehensive review of the existing work in ABSA with a focus in the education domain. A wide range of methodologies are discussed and conclusions are drawn.

Large content providers and content distribution network operators usually connect with large Internet service providers (eyeball networks) through dedicated private peering. The capacity of these private network interconnects is provisioned to match the volume of the real content demand by the users. Unfortunately, in case of a surge in traffic demand, for example due to a content trending in a certain country, the capacity of the private interconnect may deplete and the content provider/distributor would have to reroute the excess traffic through transit providers. Although, such overflow events are rare, they have significant negative impacts on content providers, Internet service providers, and end-users. These include unexpected delays and disruptions reducing the user experience quality, as well as direct costs paid by the Internet service provider to the transit providers. If the traffic overflow events could be predicted, the Internet service providers would be able to influence the routes chosen for the excess traffic to reduce the costs and increase user experience quality. In this article we propose a method based on an ensemble of deep learning models to predict overflow events over a short term horizon of 2-6 hours and predict the specific interconnections that will ingress the overflow traffic. The method was evaluated with 2.5 years' traffic measurement data from a large European Internet service provider resulting in a true-positive rate of 0.8 while maintaining a 0.05 false-positive rate. The lockdown imposed by the COVID-19 pandemic reduced the overflow prediction accuracy. Nevertheless, starting from the end of April 2020 with the gradual lockdown release, the old models trained before the pandemic perform equally well.

Recently, the automatic prediction of personality traits has received increasing attention and has emerged as a hot topic within the field of affective computing. In this work, we present a novel deep learning-based approach for automated personality detection from text. We leverage state of the art advances in natural language understanding, namely the BERT language model to extract contextualized word embeddings from textual data for automated author personality detection. Our primary goal is to develop a computationally efficient, high performance personality prediction model which can be easily used by a large number of people without access to huge computation resources. Our extensive experiments with this ideology in mind, led us to develop a novel model which feeds contextualized embeddings along with psycholinguistic features to a Bagged-SVM classifier for personality trait prediction. Our model outperforms the previous state of the art by 1.04% and, at the same time is significantly more computationally efficient to train. We report our results on the famous gold standard Essays dataset for personality detection.

Intelligent robots need to achieve abstract objectives using concrete, spatiotemporally complex sensory information and motor control. Tabula rasa deep reinforcement learning (RL) has tackled demanding tasks in terms of either visual, abstract, or physical reasoning, but solving these jointly remains a formidable challenge. One recent, unsolved benchmark task that integrates these challenges is Mujoban, where a robot needs to arrange 3D warehouses generated from 2D Sokoban puzzles. We explore whether integrated tasks like Mujoban can be solved by composing RL modules together in a sense-plan-act hierarchy, where modules have well-defined roles similarly to classic robot architectures. Unlike classic architectures that are typically model-based, we use only model-free modules trained with RL or supervised learning. We find that our modular RL approach dramatically outperforms the state-of-the-art monolithic RL agent on Mujoban. Further, learned modules can be reused when, e.g., using a different robot platform to solve the same task. Together our results give strong evidence for the importance of research into modular RL designs. Project website: https://sites.google.com/view/modular-rl/

Adversarial training is currently the most powerful defense against adversarial examples. Previous empirical results suggest that adversarial training requires wider networks for better performances. Yet, it remains elusive how does neural network width affects model robustness. In this paper, we carefully examine the relation between network width and model robustness. We present an intriguing phenomenon that the increased network width may not help robustness. Specifically, we show that the model robustness is closely related to both natural accuracy and perturbation stability, a new metric proposed in our paper to characterize the model's stability under adversarial perturbations. While better natural accuracy can be achieved on wider neural networks, the perturbation stability actually becomes worse, leading to a potentially worse overall model robustness. To understand the origin of this phenomenon, we further relate the perturbation stability with the network's local Lipschitznesss. By leveraging recent results on neural tangent kernels, we show that larger network width naturally leads to worse perturbation stability. This suggests that to fully unleash the power of wide model architecture, practitioners should adopt a larger regularization parameter for training wider networks. Experiments on benchmark datasets confirm that this strategy could indeed alleviate the perturbation stability issue and improve the state-of-the-art robust models.

Gaming, cloud computing, GPT-3; Microsoft has been all over the news this week. Undeterred by TikTok's ditch, the company made a more ambitious and probably better purchase in the form of Bethesda Softworks, a behemoth of the gaming industry. However, Amazon played a last minute spoilsport by announcing its own cloud gaming service. Read more about the most happening events in the tech industry in this week's top news brought to you by Analytics India Magazine. The saga of algorithms and their biases took a new turn when the Twitter users stumbled upon the mysterious cropping mechanism on the platform.

Louis Columbus in 10 Ways AI Is Going To Improve Fintech In 2020 stated that "Bottom Line: AI & machine learning will improve Fintech in 2020 by increasing the accuracy and personalization of payment, lending, and insurance services while also helping to discover new borrower pools." Since that time the Covid-19 crisis and tragedy arose. On the one hand Paul Clarke noted that UK fintech investment slumps by 40% amid Covid-19 crisis, whilst on the other Deloitte in Beyond COVID-19: New opportunities for Fintech companies note that "As the COVID-19 pandemic continues to create uncertainty, many fintechs are under stress on a number of fronts. But, as the broader economy shifts from "respond" to "recover", new opportunities may be created for some fintechs. A key question is how fintechs may leverage their unique assets and skills to seize new opportunities in the future. It could be an opportune time to think big and act boldly." Pavrita R considered the impact of Covid-19 and noted in 5 U.S. FinTech startups reimagining the healthcare industry notes that FinTech is undoubtedly shaping the face of the Health Care industry. "FinTech companies leverage powerful innovations blockchain, Artificial Intelligence, and Machine Learning to eliminate the inefficiencies and knowledge gaps endemic to most healthcare payment plans." The likes of Nigel Wilson (@nigewillson) and Brian Ahier (@ahier) have stressed the importance to apply AI to positive use cases such as preventative medicine and improved Health Care outcomes. McKinsey in an article entitled AI-bank of the future: Can banks meet the AI challenge? " The potential for value creation is one of the largest across industries, as AI can potentially unlock $1 trillion of incremental value for banks, annually (Exhibit 1)." Source for image above: AI-bank of the future: Can banks meet the AI challenge? "While for many financial services firms, the use of AI is episodic and focused on specific use cases, an increasing number of banking leaders are taking a comprehensive approach to deploying advanced AI, and embedding it across the full lifecycle, from the front- to the back-office (Exhibit 2)" Source for image above: AI-bank of the future: Can banks meet the AI challenge? The Covid-19 crisis is a challenge both in terms of human health and also to the Fintech world.

While massive language models like GPT-3 have impressed the public with its extraordinary capabilities in composing articles, short shorties, songs and poems, many have severely scrutinised the technology as a mere parlour trick. However, researchers at Allen Institute for Artificial Intelligence (AI2) believe that the underlying technology that has been used to develop GPT-3 can have immense potential to advance AI as a whole. GPT-3 is a text-based model, which has been trained on an enormous amount of internet data, but researchers at AI2 utilised the same methods to train both texts as well as images. To take this idea forward, the researchers developed a visual language model -- X-LXMERT, which can generate images, if provided with a caption. The model can run both on texts as well as images; however, the outcome images aren't as realistic as generated by GANs.