Related papers: Adviser Networks: Learning What Question to Ask fo…

A central concern in an interactive intelligent system is optimization of its actions, to be maximally helpful to its human user. In recommender systems for instance, the action is to choose what to recommend, and the optimization task is…

We propose a novel mixture-of-experts class to optimize computer vision models in accordance with data transfer limitations at test time. Our approach postulates that the minimum acceptable amount of data allowing for highly-accurate…

The currently leading artificial neural network models of the visual ventral stream - which are derived from a combination of performance optimization and robustification methods - have demonstrated a remarkable degree of behavioral…

A multitude of explainability methods and associated fidelity performance metrics have been proposed to help better understand how modern AI systems make decisions. However, much of the current work has remained theoretical -- without much…

When machine predictors can achieve higher performance than the human decision-makers they support, improving the performance of human decision-makers is often conflated with improving machine accuracy. Here we propose a framework to…

Many high-stake decisions follow an expert-in-loop structure in that a human operator receives recommendations from an algorithm but is the ultimate decision maker. Hence, the algorithm's recommendation may differ from the actual decision…

Human visual system can selectively attend to parts of a scene for quick perception, a biological mechanism known as Human attention. Inspired by this, recent deep learning models encode attention mechanisms to focus on the most…

Fully automatic deep learning has become the state-of-the-art technique for many tasks including image acquisition, analysis and interpretation, and for the extraction of clinically useful information for computer-aided detection,…

Deep Neural Networks have been successfully used for the task of Visual Question Answering for the past few years owing to the availability of relevant large scale datasets. However these datasets are created in artificial settings and…

As machines have become more intelligent, there has been a renewed interest in methods for measuring their intelligence. A common approach is to propose tasks for which a human excels, but one which machines find difficult. However, an…

Modeling and prediction of human motion dynamics has long been a challenging problem in computer vision, and most existing methods rely on the end-to-end supervised training of various architectures of recurrent neural networks. Inspired by…

The exponential growth of volume, variety and velocity of data is raising the need for investigations of automated or semi-automated ways to extract useful patterns from the data. It requires deep expert knowledge and extensive…

We present a challenging benchmark for the Open WorLd VISual question answering (OWLViz) task. OWLViz presents concise, unambiguous queries that require integrating multiple capabilities, including visual understanding, web exploration, and…

Recommender systems are a vital tool that helps us to overcome the information overload problem. They are being used by most e-commerce web sites and attract the interest of a broad scientific community. A recommender system uses data on…

Humans should be able work more effectively with artificial intelligence-based systems when they can predict likely failures and form useful mental models of how the systems work. We conducted a study of human's mental models of artificial…

In many practical applications of AI, an AI model is used as a decision aid for human users. The AI provides advice that a human (sometimes) incorporates into their decision-making process. The AI advice is often presented with some measure…

Neural nets are powerful function approximators, but the behavior of a given neural net, once trained, cannot be easily modified. We wish, however, for people to be able to influence neural agents' actions despite the agents never training…

Explaining artificial intelligence (AI) predictions is increasingly important and even imperative in many high-stakes applications where humans are the ultimate decision-makers. In this work, we propose two novel architectures of…

Many vision and language models suffer from poor visual grounding - often falling back on easy-to-learn language priors rather than basing their decisions on visual concepts in the image. In this work, we propose a generic approach called…

Acquiring mathematical skills is considered a key challenge for modern Artificial Intelligence systems. Inspired by the way humans discover numerical knowledge, here we introduce a deep reinforcement learning framework that allows to…