AI

IBM Research AI: Advancing AI for industry and society

IBM Sets New Transcription Performance Milestone on Automatic Broadcast News Captioning

IBM sets new performance records for automatic captioning of broadcast news audio, with error rates of 6.5% and 5.9% on two broadcast news benchmarks.

Continue reading

Ultra-Low-Precision Training of Deep Neural Networks

IBM researchers introduce accumulation bit-width scaling, addressing a critical need in ultra-low-precision hardware for training deep neural networks.

Continue reading

Leveraging Temporal Dependency to Combat Audio Adversarial Attacks

A new approach to defend against adversarial attacks in non-image tasks, such as audio input and automatic speech recognition.

Continue reading

Unifying Continual Learning and Meta-Learning with Meta-Experience Replay

Meta-Experience Replay (MER) integrates meta-learning and experience replay to achieve state-of-the-art performance on continual learning benchmarks.

Continue reading

Will Adam Algorithms Work for Me?

A simple and effective approach to monitor the convergence of Adam algorithms, a generic class of adaptive gradient methods for non-convex optimization.

Continue reading

IBM Project Debater Visits the UN

Can AI capture the narrative of a global population on a controversial topic? IBM brings Project Debater to the AI for Social Good summit to find out.

Continue reading

IBM Research AI Advancing, Trusting, and Scaling Learning at ICLR

IBM researchers present recent work on advancing, trusting, and scaling learning at the annual International Conference on Learning Representations (ICLR).

Continue reading

IBM Research AI at CHI 2019

At the ACM CHI Conference on Human Factors in Computing Systems, IBM researchers present recent work in human-computer interaction in the context of AI.

Continue reading

IBM Research at the Intersection of HCI and AI

IBM research on explainable AI, human-computer interaction (HCI), and automated ML featured at this year's conference on Intelligent User Interfaces.

Continue reading

Highly Accurate Deep Learning Inference with 2-bit Precision

IBM Research shares new results at SysML that push the envelope for deep learning inference, enabling high accuracy down to 2-bit precision.

Continue reading

Dialog-Based Interactive Image Retrieval

A natural language-based system for interactive image retrieval that is more expressive than conventional systems based on binary or fixed-form feedback.

Continue reading

Think 2019 Kicks Off with Live Debate Between Man and Machine

Today, an artificial intelligence (AI) system engaged in a live, public debate with a human debate champion at Think 2019 in San Francisco.

Continue reading