AI

IBM Research AI: Advancing AI for industry and society

Pruning AI networks without performance loss

In a spotlight paper from the 2017 NIPS Conference, my team and I presented an AI optimization framework we call Net-Trim, which is a layer-wise convex scheme to prune a pre-trained deep neural network. Deep learning has become a method of choice for many AI applications, ranging from image recognition to language translation. Thanks to […]

Continue reading

Distributing Control of Deep Learning Training Delivers 10x Performance Improvement

My IBM Research AI team and I recently completed the first formal theoretical study of the convergence rate and communications complexity associated with a decentralized distributed approach in a deep learning training setting. The empirical evidence proves that in specific configurations, a decentralized approach can result in a 10x performance boost over a centralized approach […]

Continue reading

Making interaction with AI systems more natural with textual grounding

In an upcoming oral presentation at the 2017 Neural Information Processing Systems (NIPS) Conference, our teams from the University of Illinois at Urbana-Champaign and IBM Research AI have proposed a new supervised learning algorithm to solve a well-known problem in AI called textual grounding. Imagine you wanted to ask someone to hand you an object. […]

Continue reading

TJBot goes digital, and more playground adventures

Last November we introduced TJBot – an open source, programmable cardboard robot powered by Watson services – to help demonstrate what’s possible with artificial intelligence. Outfitted with a camera, microphone, speaker, servo and LED, TJBot has charmed makers, developers, students and creators of all ages.  The global community of TJBot enthusiasts continues to grow, as […]

Continue reading

The future of hardware is AI

To make great strides in AI, hardware must change. Starting with GPUs, and then evolving to analog devices, and then fault tolerant quantum computers.

Continue reading

Reducing discrimination in AI with new methodology

A new methodology from IBM Research AI reduces the discrimination present in datasets used to train AI algorithms to cut down bias.

Continue reading

How dictionaries act as strong foundations for training AI systems

Similar to the way people consult dictionaries to define the meaning and context of words, artificial intelligence (AI) systems rely on good quality entity dictionaries or, more importantly, being able to build up-to-date ones for any given concept. In fact, in many Information Extraction (IE) tasks, a powerful building block for any sophisticated extraction is […]

Continue reading

Publishing in The Lancet’s EBioMedicine: New research in AI pushes frontiers in epileptic seizure prediction

Today, The Lancet’s EBioMedicine journal will publish a study led by scientists from IBM Research-Australia and the University of Melbourne marking important progress in personalized seizure forecasting with AI. The findings, described in a paper titled ‘Epileptic Seizure Prediction using Big Data and Deep Learning: Toward a Mobile System,’ present new results in epileptic seizure […]

Continue reading

IBM scientists demonstrate 10x faster large-scale machine learning using GPUs

Together with EPFL scientists, our IBM Research team has developed a scheme for training big data sets quickly. It can process a 30 Gigabyte training dataset in less than one minute using a single graphics processing unit (GPU) — a 10× speedup over existing methods for limited memory training. The results, which efficiently utilize the […]

Continue reading

Helping AI master video understanding

I am part of the team at the MIT IBM Watson AI Lab that is carrying out fundamental AI research to push the frontiers of core technologies that will advance the state-of-the-art in AI video comprehension. This is just one example of joint research we’re pursuing together to produce innovations in AI technology that solve […]

Continue reading

IBM Research showcases AI advances @ NIPS 2017

At the 2017 NIPS conference in Long Beach, CA, IBM will showcase new advances from its AI research team via technical papers as well as results from the company’s ongoing collaboration with academic institutions through the MIT IBM Watson AI Lab and the AI Horizons Network. IBM and MIT scientists will unveil and publish a […]

Continue reading