Image recognition accuracy: An unseen challenge confounding today’s AI
“Minimum viewing time” benchmark gauges image recognition complexity for AI systems by measuring the time needed for accurate human identification.
Research
Computational model captures the elusive transition states of chemical reactions
Using generative AI, MIT chemists created a model that can predict the structures formed when a chemical reaction reaches its point of no return.
Deep neural networks show promise as models of human hearing
Study shows computational models trained to perform auditory tasks display an internal organization similar to that of the human auditory cortex.
Closing the design-to-manufacturing gap for optical devices
A new method enables optical devices that more closely match their design specifications, boosting accuracy and efficiency.
Automated system teaches users when to collaborate with an AI assistant
MIT researchers develop a customized onboarding process that helps a human learn when a model’s advice is trustworthy.
MIT engineers develop a way to determine how the surfaces of materials behave
Using machine learning, the computational method can provide details of how materials work as catalysts, semiconductors, or battery components.
AI accelerates problem-solving in complex scenarios
A new, data-driven approach could lead to better solutions for tricky optimization problems like global package routing or power grid operation.
New method uses crowdsourced feedback to help train robots
Human Guided Exploration (HuGE) enables AI agents to learn quickly with some help from humans, even if the humans make mistakes.
Search algorithm reveals nearly 200 new kinds of CRISPR systems
By analyzing bacterial data, researchers have discovered thousands of rare new CRISPR systems that have a range of functions and could enable gene editing, diagnostics, and more.
Synthetic imagery sets new bar in AI training efficiency
MIT CSAIL researchers innovate with synthetic imagery to train AI, paving the way for more efficient and bias-reduced machine learning.