Our new paper, NEVIS’22: A Stream of 100 Tasks Sampled From 30 Years of Computer Vision Research, proposes a playground to study the question of efficient knowledge transfer in a controlled and reproducible setting. The Never-Ending Visual classification Stream (NEVIS’22)…
Most artificial intelligence (AI) researchers now believe that writing computer code which can capture the nuances of situated interactions is impossible. Alternatively, modern machine learning (ML) researchers have focused on learning about these types of interactions from data. To explore…
Research finds using a large collection of simple, un-curated synthetic image generation programs to pretrain a computer vision model for image classification yields greater accuracy than employing other pretraining methods that are more costly and time consuming, and less scalable.…
A new technique enables artificial intelligence agents to think much farther into the future when considering how their behaviors can influence the behaviors of other AI agents, toward the completion of a task. This approach improves long-term performance of cooperative…
Quantum computers promise significantly shorter computing times for complex problems. But there are still only a few quantum computers worldwide with a limited number of so-called qubits. However, quantum computer algorithms can already run on conventional servers that simulate a…
Researchers have developed a new model to describe how biological or technical systems form complex structures without external guidance. Read More
Posted by Mohammad Saleh, Software Engineer, Google Research, Brain Team, and Yinan Wang, Software Engineer, Google Workspace Information overload is a significant challenge for many organizations and individuals today. It can be overwhelming to keep up with incoming chat messages…
Researchers discuss how mimicking sleep patterns of the human brain in artificial neural networks may help mitigate the threat of catastrophic forgetting in the latter, boosting their utility across a spectrum of research interests. Read More
Inspired by the biomechanics of the manta ray, researchers have developed an energy-efficient soft robot that can swim more than four times faster than previous swimming soft robots. The robots are called ‘butterfly bots,’ because their swimming motion resembles the…
Posted by Mahima Pushkarna, Senior Interaction Designer, and Andrew Zaldivar, Senior Developer Relations Engineer, Google Research As machine learning (ML) research moves toward large-scale models capable of numerous downstream tasks, a shared understanding of a dataset’s origin, development, intent, and…