Search

A new technique could enable a robot to manipulate squishy objects like pizza dough or soft materials like clothing.

This report presents an overview of how machine learning is rapidly advancing clinical translational imaging in ways that will aid in the early detection, prediction, and treatment of diseases that threaten brain health. Towards this goal, we aresharing the information presented at a symposium,...

Current demand for accountability and efficiency of healthcare organizations, combined with the greater availability of routine data on clinical care and outcomes, has led to an increased focus on statistical methods in healthcare regulation. We consider three different regulatory functions in which...

The increased use of machine learning to assist with decision-making in high-stakes domains has been met with both enthusiasm and concern. One source of ongoing debate is the effect and value of decision makers' discretionary power to override algorithmic recommendations. In this paper, we study the...

Mapping out meteorites in Antarctica: scientists’ bid to uncover our solar system’s deep past

A new technique compares the reasoning of a machine-learning model to that of a human, so the user can see patterns in the model’s behavior.

Anatomical segmentation is a fundamental task in medical image computing, generally tackled with fully convolutional neural networks which produce dense segmentation masks. These models are often trained with loss functions such as cross-entropy or Dice, which assume pixels to be independent of each...

As language technologies become more ubiquitous, there are increasing efforts towards expanding the language diversity and coverage of natural language processing (NLP) systems. Arguably, the most important factor influencing the quality of modern NLP systems is data availability. In this work, we...

A new technique for removing bias in datasets can enable machine-learning models to make loan approval predictions that are both fair and accurate.

Background

Proximal femoral fractures are an important clinical and public health issue associated with substantial morbidity and early mortality. Artificial intelligence might offer improved diagnostic accuracy for these fractures, but typical approaches to testing of artificial intelligence...

Artificial intelligence systems for health care, like any other medical device, have the potential to fail. However, specific qualities of artificial intelligence systems, such as the tendency to learn spurious correlates in training data, poor generalisability to new deployment settings, and a...

Estimating the pose of multiple animals is a challenging computer vision problem: frequent interactions cause occlusions and complicate the association of detected keypoints to the correct individuals, as well as having highly similar looking animals that interact more closely than in typical multi...

Real-world sequential decision-making tasks are generally complex, requiring trade-offs between multiple, often conflicting, objectives. Despite this, the majority of research in reinforcement learning and decision-theoretic planning either assumes only a single objective, or that multiple...

When artificial intelligence is tasked with visually identifying objects and faces, it assigns specific components of its network to face recognition — just like the human brain.

The fundamental challenge in causal induction is to infer the underlying graph structure given observational and/or interventional data. Most existing causal induction algorithms operate by generating candidate graphs and then evaluating them using either score-based methods (including continuous...

Models can fail in unpredictable ways during deployment due to task ambiguity, when multiple behaviors are consistent with the provided training data. An example is an object classifier trained on red squares and blue circles: when encountering blue squares, the intended behavior is undefined. We...

Pruning neural networks at initialization would enable us to find sparse models that retain the accuracy of the original network while consuming fewer computational resources for training and inference. However, current methods are insufficient to enable this optimization and lead to a large...

Research in computer analysis of medical images bears many promises to improve patients’ health. However, a number of systematic challenges are slowing down the progress of the field, from limitations of the data, such as biases, to research incentives, such as optimizing for publication. In this...

MIT CSAIL scientists created an algorithm to solve one of the hardest tasks in computer vision: assigning a label to every pixel in the world, without human supervision.

The reinforcement learning (RL) problem is rife with sources of non-stationarity, making it a notoriously difficult problem domain for the application of neural networks. We identify a mechanism by which non-stationary prediction targets can prevent learning progress in deep RL agents: \textit...