A new study from researchers at MIT and Brown University characterizes several properties that emerge during the training of deep classifiers, a type of artificial neural network commonly used for classification tasks such as image classification, speech recognition, and natural language processing. The paper, “Dynamics in Deep Classifiers trained with the Square Loss: Normalization, Low…
Posted by Shangbang Long, Software Engineer, Google Research The last few decades have witnessed the rapid development of Optical Character Recognition (OCR) technology, which has evolved from an academic benchmark task used in early breakthroughs of deep learning research to tangible products available in consumer devices and to third party developers for daily use. These…
Posted by Yu Zhang, Research Scientist, and James Qin, Software Engineer, Google Research Last November, we announced the 1,000 Languages Initiative, an ambitious commitment to build a machine learning (ML) model that would support the world’s one thousand most-spoken languages, bringing greater inclusion to billions of people around the globe. However, some of these languages…
Posted by Krzysztof Choromanski, Staff Research Scientist, Robotics at Google, and Xuesu Xiao, Visiting Researcher, George Mason University Despite decades of research, we don’t see many mobile robots roaming our homes, offices, and streets. Real-world robot navigation in human-centric environments remains an unsolved problem. These challenging situations require safe and efficient navigation through tight spaces,…
Turns out, even language models “think” they’re biased. When prompted in ChatGPT, the response was as follows: “Yes, language models can have biases, because the training data reflects the biases present in society from which that data was collected. For example, gender and racial biases are prevalent in many real-world datasets, and if a language…
When OpenAI launched ChatGPT, with zero fanfare, in late November 2022, the San Francisco–based artificial-intelligence company had few expectations. Certainly, nobody inside OpenAI was prepared for a viral mega-hit. The firm has been scrambling to catch up—and capitalize on its success—ever since. It was viewed in-house as a “research preview,” says Sandhini Agarwal, who works…
In a packed room in MIT’s Stata Center, hundreds of digital robots collide across a giant screen projected at the front of the room. A crowd of students in the audience gasps and cheers as the battle’s outcome hangs in the balance. In an upper corner of the screen, the people who have programmed the…
Posted by Florian Hartmann, Software Engineer, and Peter Kairouz, Research Scientist, Google Research Federated learning is a distributed way of training machine learning (ML) models where data is locally processed and only focused model updates and metrics that are intended for immediate aggregation are shared with a server that orchestrates training. This allows the training…
Modern fabrication tools such as 3D printers can make structural materials in shapes that would have been difficult or impossible using conventional tools. Meanwhile, new generative design systems can take great advantage of this flexibility to create innovative designs for parts of a new building, car, or virtually any other device. But such “black box”…
Posted by Minji Yoon, Research Intern, and Bryan Perozzi, Research Scientist, Google Research, Graph Mining Team Industrial applications of machine learning are commonly composed of various items that have differing data modalities or feature distributions. Heterogeneous graphs (HGs) offer a unified view of these multimodal data systems by defining multiple types of nodes (for each…