TAPAS: Frugally Predicting the Accuracy of a Neural Network Prior...


TAPAS can estimate the classification performance of a neural network for unseen input datasets in fractions of a second, without training.

Continue reading

IBM Research-Zurich

December 14, 2018

AI Year in Review: Highlights of Papers and Predictions from...


Highlights from IBM Research AI in 2018 in three key areas - advancing, scaling and trusting AI - and predictions about what's to come in 2019.

Continue reading

AI

December 13, 2018

Could AI Help People Change Their Behaviour?


An open-source AI algorithm to help people change their habits, based on an ontology developed by behavioural scientists at University College London.

Continue reading

Healthcare

December 12, 2018

IBM Research, Hello Tractor Pilot Agriculture Digital Wallet based on...


Scientists at our lab in Kenya are working with Hello Tractor, a mobile platform that enables farmers to access tractor services on demand.

Continue reading

Agriculture

December 11, 2018

IBM’s AI Experiments Hub Puts Cutting-Edge Technology in Your Hands


IBM Research launches new AI Experiments hub featuring prototypes of tools and resources that will unleash the power of AI.

Continue reading

AI

December 10, 2018

Efficient Deep Learning Training on the Cloud with Small Files


An approach to efficiently train deep learning models on cloud platforms when the training dataset consists of a large number of small files.

Continue reading

Cloud Computing

December 5, 2018

8-Bit Precision for Training Deep Learning Systems


IBM scientists show, for the first time, successful training of deep neural networks using 8-bit floating point numbers while fully maintaining accuracy.

Continue reading

AI

December 3, 2018

Interpretability and Performance: Can the Same Model Achieve Both?


Bridging the gap between interpretability and performance by transferring information from a high-performing model to a simpler, interpretable model.

Continue reading

AI

December 3, 2018

Dual 8-Bit Breakthroughs Bring AI to the Edge


IBM researchers showcase new 8-bit breakthroughs in hardware that will take AI further than it’s been before: right to the edge.

Continue reading

AI

December 3, 2018

Algebraic Gradient-Based Solver (AGS): A Novel Solver for Approximate Marginal...


The Algebraic Gradient-based Solver (AGS), a novel solver for approximate marginal MAP inference, shows how ideas from planning can be used for inference.

Continue reading

IBM Research-Ireland

November 29, 2018

Delta-Encoder: Synthesizing a Full Set of Samples From One Image


Delta-encoder enables AI to classify an image from a new category with only a limited number of examples from that category.

Continue reading

AI

November 27, 2018