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.
December 13, 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.
December 10, 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.
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.
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.
December 3, 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.
November 27, 2018
IBM Research AI at 2018 Conference on Neural Information Processing...
IBM Research AI shares new ideas and research results at the Thirty-Second Conference on Neural Information Processing Systems in Montreal.
November 20, 2018
Probabilistic Programming with Pyro in WML
How to write a probabilistic model using Pyro, a deep probabilistic programming language built on PyTorch, and run it via IBM Watson Machine Learning.
November 7, 2018
Probabilistic Programming with Edward in WML
IBM scientists explain how to run Edward code, a deep probabilistic programming language, on the IBM Watson Machine Learning (WML) platform.
November 2, 2018
Graph2Seq: A Generalized Seq2Seq Model for Graph Inputs
IBM scientists demonstrate the advantages of the Graph2Seq model for semantic parsing and natural language generation at EMNLP 2018.
November 1, 2018
Word Mover’s Embedding: Universal Text Embedding from Word2Vec
Word Mover’s Embedding is an unsupervised framework for learning universal text embeddings that can be used for downstream tasks.
November 1, 2018