Page 2 - Neural Information Processing News Today

Web publication for "Discovered Policy Optimisation".

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 or competitive AI agents.

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.

IIT Indore director Prof Suhas S Joshi delivered the opening address and remarked that the conference is focusing on a very important area that has the potential to benefit society in a big way

Machine-learning models trained to classify human actions using synthetic data can outperform models trained using real data in certain situations. This could help scientists identify when it’s better to use synthetic data for training, which could eliminate bias, privacy, security, and copyright issues that often impact real datasets.

MIT researchers developed a machine-learning technique that captures and models the underlying acoustics of a scene from a limited number of sound recordings. The system can accurately simulate what any sound, like a song, would sound like if a person were to walk around to different locations in a scene.

A new technique enables on-device training of machine-learning models on edge devices like microcontrollers, which have very limited memory. This could allow edge devices to continually learn from new data, eliminating data privacy issues, while enabling user customization.

In this day and age, they have left no professional field unoccupied — with passion and overwhelming success

NYU data expert Meredith Broussard explains why inclusivity starts in the programming code itself.

MIT scientists discover that contemporary deep-learning methods confidently recognize images that are nonsense, which could be concerning for medical and autonomous driving decision-making.