Search

Over the past few years, many artists have started to use what’s called “neural network software” to create works of art.

Users input existing images into the software, which has been programmed to analyze them, learn a specific aesthetic and spit out new images that artists can curate. By…

We propose learning from teleoperated play data (LfP) as a way to scale up multi-task robotic skill learning. Learning from play (LfP) offers three main advantages: 1) It is cheap. Large amounts of play data can be collected quickly as it does not require scene staging, task segmenting, or resetting...

We introduce GQA, a new dataset for real-world visual reasoning and compositional question answering, seeking to address key shortcomings of previous VQA datasets. We have developed a strong and robust question engine that leverages scene graph structures to create 22M diverse reasoning questions...

Coming up with useful applications of Machine Learning can be an exciting and complicated problem. Sure, I can do the same linear regression problem everyone does, with the same data, but if I'm not excited about what I'm creating, how can I expect anyone else to be interested?

Then I got the…

The biggest lesson that can be read from 70 years of AI research is that general methods that leverage computation are ultimately the most effective, and by a large margin. The ultimate reason for this is Moore's law, or rather its generalization of continued exponentially falling cost per unit of…

Maike Sonnewald adapts a method that identifies areas of the global ocean with similar physics, revealing global dynamical regimes.

Image captioning models have achieved impressive results on datasets containing limited visual concepts and large amounts of paired image-caption training data. However, if these models are to ever function in the wild, a much larger variety of visual concepts must be learned, ideally from less...

We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout. Previous methods directly feed the semantic layout as input to the deep network, which is then processed through stacks of convolution, normalization, and...

“You are the average of the five people you spend the most time with.”

“Your network is your net worth.”

However you phrase it, the truism holds for everyone: the people you associate with on a regular basis play a major role in helping you solve problems and meet goals. It only stands to reason…

Technique could improve machine-learning tasks in protein design, drug testing, and other applications.

Algorithm designs optimized machine-learning models up to 200 times faster than traditional methods.

Surviving an extinction-level event requires adapting to a new environment.

Word embeddings are widely used in NLP for a vast range of tasks. It was shown that word embeddings derived from text corpora reflect gender biases in society. This phenomenon is pervasive and consistent across different word embedding models, causing serious concern. Several recent works tackle...

With public and academic attention increasingly focused on the new role of machine learning in the health information economy, an unusual and no-longer-esoteric category of vulnerabilities in machine-learning systems could prove important. These vulnerabilities allow a small, carefully designed...

Machine learning can reveal optimal growing conditions to maximize taste and other features.

Counting search queries isn’t easy, but MIT CSAIL’s new LearnedSketch system for “frequency-estimation” aims to help.

Researchers combine statistical and symbolic artificial intelligence techniques to speed learning and improve transparency.

Robust detection and tracking of objects is crucial for the deployment of autonomous vehicle technology. Image-based benchmark datasets have driven the development in computer vision tasks such as object detection, tracking and segmentation of agents in the environment. Most autonomous vehicles...

Gestures in music are of paramount importance partly because they are directly linked to musicians' sound and expressiveness. At the same time, current motion capture technologies are capable of detecting body motion/gestures details very accurately. We present a machine learning approach to...

Localized structures in nano- and sub-nano-scales strongly affect material properties. Thus, some spectroscopic techniques have been used to characterize local atomic and electronic structures. If material properties can be directly 'measured' via spectral observations, the atomic-scale...