deep learning

Distributed Software-Defined Networking Control by Deep Reinforcement Learning for 5G and Beyond

IEEE ICC 2019 “Best Paper” details novel deep reinforcement learning approach to maximize overall performance of Software-Defined Networking that supports 5G.

Continue reading

AI Models Predict Breast Cancer with Radiologist-Level Accuracy

Our team of IBM researchers published research in Radiology around a new AI model that can predict the development of malignant breast cancer in patients within the year, at rates comparable to human radiologists.

Continue reading

High-Efficiency Distributed Learning for Speech Modeling

A distributed deep learning architecture for automatic speech recognition that shortens run time without compromising model accuracy.

Continue reading

NeuNetS: Automating Neural Network Model Synthesis for Broader Adoption of AI

NeuNetS uses AI to automatically synthesize deep neural networks faster and more easily than ever before, scaling up the deployment and adoption of AI.

Continue reading

Efficient Deep Learning Training on the Cloud with Small Files

Here I describe an approach to efficiently train deep learning models on machine learning cloud platforms (e.g., IBM Watson Machine Learning) when the training dataset consists of a large number of small files (e.g., JPEG format) and is stored in an object store like IBM Cloud Object Storage (COS). As an example, I train a […]

Continue reading

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

Delta-encoder is a novel approach for few- and one-shot object recognition, in which a modified auto-encoder (called delta-encoder) extracts transferable intra-class deformations (deltas) between same-class pairs of training examples, then applies them to a few examples of a new class (unseen during training) to efficiently synthesize samples from that class. The synthesized samples are then […]

Continue reading

Probabilistic Programming with Pyro in WML

In a previous post we explained how to write a probabilistic model using Edward and run it on the IBM Watson Machine Learning (WML) platform. In this post, we discuss the same example written in Pyro, a deep probabilistic programming language built on top of PyTorch. Deep probabilistic programming languages (DPPLs) such as Edward and […]

Continue reading

Probabilistic Programming with Edward in WML

Edward is a deep probabilistic programming language (DPPL), that is, a language for specifying both deep neural networks and probabilistic models. DPPLs draw upon programming languages, Bayesian statistics, and deep learning to ease the development of powerful AI applications. Probabilistic languages let the user express a probabilistic model as a program with an intuitive formalism […]

Continue reading

AI and the Eye: Deep Learning for Glaucoma Detection

Glaucoma is the second leading cause of blindness in the world, impacting approximately 2.7 million people in the U.S alone [1]. It is a complex set of diseases and, if left untreated, can lead to blindness. It’s a particularly large issue in Australia, where only 50% of all people who have it are actually diagnosed […]

Continue reading

Helping to Improve Medical Image Analysis with Deep Learning

Medical imaging creates tremendous amounts of data: many emergency room radiologists must examine as many as 200 cases each day, and some medical studies contain up to 3,000 images. Each patient’s image collection can contain 250GB of data, ultimately creating collections across organizations that are petabytes in size. Within IBM Research, we see potential in […]

Continue reading

Using AI to Design Deep Learning Architectures

Selecting the best architecture for deep learning architectures is typically a time-consuming process that requires expert input, but using AI can streamline this process. I am developing an evolutionary algorithm for architecture selection that is up to 50,000 times faster than other methods, with only a small increase in error rate. Deep learning models are […]

Continue reading

Disentanglement of Latent Factors of Variation with Deep Learning

The ability to infer abstract high-level concepts from raw sensory inputs is a key part of human intelligence. Developing models that recapitulate this ability is an important goal in AI research. A fundamental challenge in this respect is disentangling the underlying factors of variation that give rise to the observed data. For example, factors of […]

Continue reading