Research
How AI Creates Photorealistic Images From Text
Have you ever seen a puppy in a nest emerging from a cracked egg? What about a photo that’s overlooking a steampunk city with airships? Or a picture of two robots having a romantic evening at the movies? These might sound far-fetched, but a novel type of machine learning technology called text-to-image generation makes them …
Charting The Future Of Technology And Tomorrow’s Unknown Business Environments
Introducing the IBM Research Technology Atlas. As leaders in our industries, we’re tasked with exploring and mapping emerging markets, and how they intersect with new and ever-evolving technologies. We do this with imperfect information, in a world with ever-shifting societal, political, and environmental landscapes. To successfully navigate anything, you need tools and data, and …
Artificial Neural Networks Model Face Processing In Autism
Many of us easily recognize emotions expressed in others’ faces. A smile may mean happiness, while a frown may indicate anger. Autistic people often have a more difficult time with this task. It’s unclear why. But new research, published June 15 in The Journal of Neuroscience, sheds light on the inner workings of the brain to suggest …
Stronger Security For Smart Devices
Researchers are pushing to outpace hackers and develop stronger protections that keep data safe from malicious agents who would steal information by eavesdropping on smart devices. Much of the work done to prevent these “side-channel attacks” has focused on the vulnerability of digital processors. For instance, hackers can measure the electric current drawn …
Introducing MUGEN, A New Dataset For Multimodal Research
What the research is: What if you could search for specific video content — “sheepdogs on speedboats,” say, or “child in green hat singing the ABC song” — and receive an accurate, complete list of results, regardless of how the videos were tagged? Or, picture the reverse: You describe a scene — or upload atmospheric …
Advancing Direct Speech-To-Speech Modeling With Discrete Units
What the research is: To make it possible for people to easily understand each other while speaking in different languages, we need more than just text-based translation systems. But the conventional approach to building speech-to-speech translation systems has faced two significant shortcomings. It uses a cascaded series of steps — speech recognition, then text-to-text translation, …
Introducing CommerceMM: A New Approach To Multimodal Understanding For Online Shopping
We’ve built CommerceMM, a new approach to multimodal understanding for online shopping. Because so many product posts rely on both text and images, comprehension of multimodal data is crucial to make products more discoverable and help shoppers more easily find what they’re looking for. CommerceMM relies on a novel set of pretraining tasks, called omni …
How Machine Learning Can Support Historians Decipher Ancient Inscriptions
The origins of ancient inscriptions are often shrouded in mystery. Writing carved into stone millennia ago can be hard to read and is often missing entire sections of the text. Now a neural network, trained on thousands of existing inscriptions, could help historians figure out when and where a piece of writing comes from – …
How The Philosophy Of Mind And Consciousness Has Affected AI Research
The “brain in a jar” is a thought experiment of a disembodied human brain living in a jar of sustenance. The thought experiment explores human conceptions of reality, mind, and consciousness. This article will explore a metaphysical argument against artificial intelligence on the grounds that a disembodied artificial intelligence, or a “brain” without a body, is incompatible with …
Solving The Challenges Of Robotic Pizza-Making
Imagine a pizza maker working with a ball of dough. She might use a spatula to lift the dough onto a cutting board then use a rolling pin to flatten it into a circle. Easy, right? Not if this pizza maker is a robot. For a robot, working with a deformable object like dough is …