This paper investigates learning in a lifelong context. Lifelong learning addresses situations in which a learner faces a whole stream of learn(cid:173) ing tasks. Such scenarios provide the opportunity to transfer knowledge across multiple learning tasks, in order to generalize more accurately from less training data. In this paper, several different approaches to lifelong learning are described, and applied in an object recognition domain. It is shown that across the board, lifelong learning approaches generalize consistently more accurately from less training data, by their ability to transfer knowledge across learning tasks.

FOX Business correspondent Lydia Hu has the latest on jobs at risk as AI further develops on'America's Newsroom.' India has no plans to regulate the use and development of artificial intelligence (AI), calling the technology and its potential uses "significant and strategic" for the nation. The Indian Ministry of Electronics and IT released a statement on Wednesday in which it detailed the country's position regarding the development, potential and dangers of AI – a topic of increasing concern and interest after hundreds of industry experts signed a letter calling for a pause in development. The ministry also wrote that it "further believes that AI will have kinetic effect for the growth of entrepreneurship & business and Government is taking all necessary steps in policies and infrastructure to develop a robust AI sector in the country." India aims to position itself as a global leader on AI to "ensure responsible and transformational use of AI for all."

Echo state networks (ESN) are a novel approach to recurrent neu(cid:173) ral network training. An ESN consists of a large, fixed, recurrent "reservoir" network, from which the desired output is obtained by training suitable output connection weights. Determination of op(cid:173) timal output weights becomes a linear, uniquely solvable task of MSE minimization. This article reviews the basic ideas and de(cid:173) scribes an online adaptation scheme based on the RLS algorithm known from adaptive linear systems. As an example, a 10-th or(cid:173) der NARMA system is adaptively identified.

We validate the proposed method on several challenging databases (e.g., INRIA-Horse, ETHZ-Shape, and UIUC-People), and it outperforms the state-of-the-arts approaches.

Machine learning-based wearable human activity recognition (WHAR) models enable the development of various smart and connected community applications such as sleep pattern monitoring, medication reminders, cognitive health assessment, sports analytics, etc. However, the widespread adoption of these WHAR models is impeded by their degraded performance in the presence of data distribution heterogeneities caused by the sensor placement at different body positions, inherent biases and heterogeneities across devices, and personal and environmental diversities. Various traditional machine learning algorithms and transfer learning techniques have been proposed in the literature to address the underpinning challenges of handling such data heterogeneities. Domain adaptation is one such transfer learning techniques that has gained significant popularity in recent literature. In this paper, we survey the recent progress of domain adaptation techniques in the Inertial Measurement Unit (IMU)-based human activity recognition area, discuss potential future directions.

Deep learning has recently gained immense popularity in the Earth sciences as it enables us to formulate purely data-driven models of complex Earth system processes. Deep learning-based weather prediction (DLWP) models have made significant progress in the last few years, achieving forecast skills comparable to established numerical weather prediction (NWP) models with comparatively lesser computational costs. In order to train accurate, reliable, and tractable DLWP models with several millions of parameters, the model design needs to incorporate suitable inductive biases that encode structural assumptions about the data and modelled processes. When chosen appropriately, these biases enable faster learning and better generalisation to unseen data. Although inductive biases play a crucial role in successful DLWP models, they are often not stated explicitly and how they contribute to model performance remains unclear. Here, we review and analyse the inductive biases of six state-of-the-art DLWP models, involving a deeper look at five key design elements: input data, forecasting objective, loss components, layered design of the deep learning architectures, and optimisation methods. We show how the design choices made in each of the five design elements relate to structural assumptions. Given recent developments in the broader DL community, we anticipate that the future of DLWP will likely see a wider use of foundation models -- large models pre-trained on big databases with self-supervised learning -- combined with explicit physics-informed inductive biases that allow the models to provide competitive forecasts even at the more challenging subseasonal-to-seasonal scales.

In this paper, we present a grammar-based natural language framework for robot programming, specifically for pick-and-place tasks. Our approach uses a custom dictionary of action words, designed to store together words that share meaning, allowing for easy expansion of the vocabulary by adding more action words from a lexical database. We validate our Natural Language Robot Programming (NLRP) framework through simulation and real-world experimentation, using a Franka Panda robotic arm equipped with a calibrated camera-in-hand and a microphone. Participants were asked to complete a pick-and-place task using verbal commands, which were converted into text using Google's Speech-to-Text API and processed through the NLRP framework to obtain joint space trajectories for the robot. Our results indicate that our approach has a high system usability score. The framework's dictionary can be easily extended without relying on transfer learning or large data sets. In the future, we plan to compare the presented framework with different approaches of human-assisted pick-and-place tasks via a comprehensive user study.

Various types of vehicle automation is increasingly used in a variety of environments including road vehicles such as cars or automated shuttles, confined areas such as mines or harbours, or in agriculture and forestry. In many use cases, the benefits are greater if several automated vehicles (AVs) cooperate to aid each other reach their goals more efficiently, or collaborate to complete a common task. Taxonomies and definitions create a common framework that helps researchers and practitioners advance the field. However, most existing work focus on road vehicles. In this paper, we review and extend taxonomies and definitions to encompass individually acting as well as cooperative and collaborative AVs for both on-road and off-road use cases. In particular, we introduce classes of collaborative vehicles not defined in existing literature, and define levels of automation suitable for vehicles where automation applies to additional functions in addition to the driving task.

The ability to explain decisions made by machine learning models remains one of the most significant hurdles towards widespread adoption of AI in highly sensitive areas such as medicine, cybersecurity or autonomous driving. Great interest exists in understanding which features of the input data prompt model decision making. In this contribution, we propose a novel approach to identify relevant features of the input data, inspired by methods from the energy landscapes field, developed in the physical sciences. By identifying conserved weights within groups of minima of the loss landscapes, we can identify the drivers of model decision making. Analogues to this idea exist in the molecular sciences, where coordinate invariants or order parameters are employed to identify critical features of a molecule. However, no such approach exists for machine learning loss landscapes. We will demonstrate the applicability of energy landscape methods to machine learning models and give examples, both synthetic and from the real world, for how these methods can help to make models more interpretable.

The combined growth of available data and their unstructured nature has received increased interest in natural language processing (NLP) techniques to make value of these data assets since this format is not suitable for statistical analysis. This work presents a systematic literature review of state-of-the-art advances using transformer-based methods on electronic medical records (EMRs) in different NLP tasks. To the best of our knowledge, this work is unique in providing a comprehensive review of research on transformer-based methods for NLP applied to the EMR field. In the initial query, 99 articles were selected from three public databases and filtered into 65 articles for detailed analysis. The papers were analyzed with respect to the business problem, NLP task, models and techniques, availability of datasets, reproducibility of modeling, language, and exchange format. The paper presents some limitations of current research and some recommendations for further research.