Try our tech

At IBM Research, we create innovative tools and resources to help unleash the power of AI. See for yourself. Take our tech for a spin.

Guarantee safety in training and testing

Verifiably Safe Reinforcement Learning (VSRL) applies advancements in symbolic reasoning combined with reinforcement learning, to ensure agents can be trusted to act safely in both training and testing.

Extract answers from COVID-19 literature using questions, not keywords

COVID-19 Literature Q&A uses machine reading comprehension to parse your questions and then surface the best answers from the CORD-19 dataset.

Securing the cloud for highly regulated industries

There’s a fatal flaw in the dominant encryption methods of today: while data is encrypted at rest and in transit, it must be decrypted during computation, leaving it exposed and vulnerable to attacks or honest but curious threat models. Fully Homomorphic Encryption (FHE) fills this critical gap, making any computation possible on fully encrypted data without ever decrypting anything.

More experiments to get your hands on

Explore novel drug candidates for COVID-19

To help researchers generate potential new drug candidates for COVID-19, we have applied our novel AI generative frameworks to three COVID-19 targets and have generated 3000 novel molecules. We are sharing these molecules under an open license here.

Quantum protein folding algorithms

IBM researchers have developed a series of quantum algorithms that show how quantum computing could improve protein folding calculations. Try your hand at testing the quantum algorithms.

CLAI aims to bring the power of AI to the command line

Your DevOps command line users can become super users with embedded AI assistants in their BASH shells. Stay in context, use NLP to get help, and automate better with AI.

GAAMA: An answer engine for your documents.

Ever wish you could search for answers in a document the same way you search for websites online? With GAAMA, you can.

Get the most out of a research paper, in less time.

Nobody can explain a paper better than the people behind the work. So, we trained the IBM Science Summarizer to leverage researchers’writings and video presentations to generate short and accurate summaries of journal publications.

Collaborate with AI to create your own work of art.

This isn’t your average paint-with-pixels editor. Explore to learn more about how neural networks compose realistic images.

Analog is back—and it's better than ever.

Go back to the future by running an experiment on IBM's one-of-a-kind analog AI chip, using phase-change memory for speed and efficiency.

Making AI more trusted, by making it explainable.

This extensible open source toolkit can help you comprehend how machine learning models predict labels by various means throughout the AI application lifecycle. 

AI has its finger on the pulse.

Project Debater - Speech by Crowd is an AI platform for crowdsourcing decision support. Share your arguments on debatable topics, and our AI constructs persuasive narratives both pro and con, giving you a fresh perspective.

Machine learning on the path to Quantum Advantage

IBM researchers have developed a series of quantum algorithms that show how entanglement can improve AI classification accuracy. Try your hand at testing the quantum algorithms to see how well they perform. 

Your AI model might be telling you this is not a cat.

Don’t let hackers interfere with your vision model. Learn more about IBM’s Adversarial Robustness Toolbox and start using it today.

Tame any bias lurking in the heart of your AI model.

Build trust in AI with IBM's AI Fairness 360 toolkit, an open-source library of metrics and algorithms to help detect and mitigate bias in AI. 

AI that builds AI.

Fast-track development of deep-learning models by using AI to automatically synthesize customized neural networks. Choose whether to optimize for speed or accuracy, and watch the model build and train itself in real time.