This paper introduces self-paced task selection to multitask learning, where instances from more closely related tasks are selected in a progression of easier-to-harder tasks, to emulate an effective human education strategy, but applied to multitask machine learning. We develop the mathematical foundation for the approach based on iterative selection of the most appropriate task, learning the task parameters, and updating the shared knowledge, optimizing a new bi-convex loss function. This proposed method applies quite generally, including to multitask feature learning, multitask learning with alternating structure optimization, etc. Results show that in each of the above formulations self-paced (easierto-harder) task selection outperforms the baseline version of these methods in all the experiments.

No abstract

In this paper, we consider the recent trend of evaluating progress on reinforcement learning technology by using text-based environments and games as evaluation environments. This reliance on text brings advances in natural language processing into the ambit of these agents, with a recurring thread being the use of external knowledge to mimic and better human-level performance. We present one such instantiation of agents that use commonsense knowledge from ConceptNet to show promising performance on two text-based environments.

This paper proposes a research direction to advance AI which draws inspiration from cognitive theories of human decision making. The premise is that if we gain insights about the causes of some human capabilities that are still lacking in AI (for instance, adaptability, generalizability, common sense, and causal reasoning), we may obtain similar capabilities in an AI system by embedding these causal components. We hope that the high-level description of our vision included in this paper, as well as the several research questions that we propose to consider, can stimulate the AI research community to define, try and evaluate new methodologies, frameworks, and evaluation metrics, in the spirit of achieving a better understanding of both human and machine intelligence. Motivation and Overall VisionAI systems have seen dramatic advancement in recent years, bringing many successful applications that are pervading our everyday life. However, we are still mostly seeing instances of narrow AI: each of these developments are typically focused on a very limited set of competences and goals, e.g., image interpretation, natural language processing, label classification, prediction, and many others. Moreover, while these successes can be accredited to improved algorithms and techniques, they are also tightly linked to the availability of huge datasets and computational power (Marcus 2020). State-of-the-art AI still lacks many capabilities that would naturally be included in a notion of intelligence, for example, if we compare these AI technologies to what human beings are able to do. Examples of these capabilities are generalizability, robustness, explainability, causal analysis, abstraction, common sense reasoning, ethics reasoning, as well as a complex and seamless integration of learning and reasoning supported by both implicit and explicit knowledge.Majority of the AI community make sturdy attempts to address the current limitations of AI and create systems that display the ability for more human-like qualities, using a variety of approaches. One of the main debates is whether endto-end neural network approaches can achieve this goal? or whether we need to integrate machine learning with symbolic and logic-based AI techniques? We believe that the integration route is the most promising, and this is supported

Disease-causing pathogens such as viruses introduce their proteins into the host cells in which they interact with the host's proteins, enabling the virus to replicate inside the host. These interactions between pathogen and host proteins are key to understanding infectious diseases. Often multiple diseases involve phylogenetically related or biologically similar pathogens. Here we present a multitask learning method to jointly model interactions between human proteins and three different but related viruses: Hepatitis C, Ebola virus, and Influenza A. Our multitask matrix completion-based model uses a shared low-rank structure in addition to a task-specific sparse structure to incorporate the various interactions. We obtain between 7 and 39 percentage points improvement in predictive performance over prior state-of-the-art models. We show how our model's parameters can be interpreted to reveal both general and specific interaction-relevant characteristics of the viruses. Our code is available online.