To better simulate how the human brain makes decisions, we’ve combined the strengths of symbolic AI and neural networks. Specifically, we combined the learning representations that neural networks create with the symbol-like entities represented by high-dimensional and distributed vectors. The idea is to guide a neural network to represent unrelated objects with dissimilar high-dimensional vectors.
Unveiled at the two-year anniversary of the IBM Research AI Hardware Center, AI Hardware Composer for analog AI hardware enables one to master and accelerate the AI hardware technology to power more sustainable AI models. It’s one of many upcoming developments of the AI Hardware Center, launched in 2019 to innovate across materials, devices, architecture and algorithms.
We use AI to automatically break down the overall application by representing application code as graphs. Our AI relies on Graph Representation Learning – a popular method in deep learning. Graphs are a natural representation for software and applications. We translated the application to a graph where the programs become nodes. Their relationships with other programs become edges and determine the boundary to separate the nodes of common business functionality.
Our team has developed Physics-informed Neural Networks (PINN) models where physics is integrated into the neural network’s learning process – dramatically boosting the AI’s ability to produce accurate results. Described in our recent paper, PINN models are made to respect physics laws that force boundaries on the results and generate a realistic output.
In newly published research, scientists integrate neural network techniques on quantum computing - combining the advantages of the two approaches - for more-accurate chemistry simulations.
IBM researchers have partnered with scientists from MIT, Northeastern University, Boston University and University of Minnesota to publish two papers on novel attacks and defenses for graph neural networks and on a new robust training algorithm called hierarchical random switching at IJCAI 2019.
A "biological" learning algorithm for neural networks that learns in an unsupervised fashion and performs well in image classification.
Researchers from MIT and IBM propose an efficient and effective method for certifying attack resistance of convolutional neural networks to given input data.
NeuNetS uses AI to automatically synthesize deep neural networks faster and more easily than ever before, scaling up the deployment and adoption of AI.
Interpretability and performance of a system are usually at odds with each other, as many of the best-performing models (viz. deep neural networks) are black box in nature. In our work, improving simple models, we try to bridge this gap by proposing a method to transfer information from a high-performing neural network to another model […]
Online social media has become one of the most important ways to communicate and exchange ideas. Unfortunately, the discourse is often crippled by abusive language that can have damaging effects on social media users. For instance, a recent survey by YouGov.uk discovered that, among the information employers can find online about job candidates, aggressive or […]
Among the various fields of exploration in artificial intelligence, deep learning is an exciting and increasingly important area of research that holds great potential for helping computers understand and extract meaning from data, e.g. deciphering images and sounds. To help further the creation and adoption of interoperable deep learning models, IBM joined the Open Neural […]