Since its introduction in the 1970s, the backpropagation algorithm (backprop) has been the workhorse for training neural networks has and contributed to impressive successes in deep learning for a wide range of applications. Backprop plays an important role in enabling neural networks to track the errors they make, learn from those mistakes and improve over […]
Understanding of the macroscopic behavior of deep learning neural networks.
At the 36th International Conference on Machine Learning (ICML 2019), June 10–15 in Long Beach, CA, IBM Research AI will present recent technical advances in machine learning for AI and data science. We’ve led the exploration and development of machine learning technologies for decades, and now we’re progressing the AI field through our portfolio of […]
IBM scientists use crowdsourcing and AI techniques to explore what different types of conversational laughter can tell us.
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.
IBM researchers introduce accumulation bit-width scaling, addressing a critical need in ultra-low-precision hardware for training deep neural networks.
A new approach to defend against adversarial attacks in non-image tasks, such as audio input and automatic speech recognition.
Meta-Experience Replay (MER) integrates meta-learning and experience replay to achieve state-of-the-art performance on continual learning benchmarks.
IBM researchers present recent work on advancing, trusting, and scaling learning at the annual International Conference on Learning Representations (ICLR).
IBM Research and New York University are using AI to analyze retina imaging data and help to assess the presence of glaucoma.