Neural architecture search is a series of machine learning techniques that can help discover optimal neural networks for a given problem.

Neural architecture search promises to speed up the process of finding neural network architectures that will yield good models for a given dataset.

For more than eighty years, deep learning has relied on a simplified model of brain function. Now, a Pittsburgh startup ...

Recent advances in neural network design have spurred the development of energy-efficient architectures for speech recognition, a field that underpins a range of modern applications from smart ...

An overview of deep learning architectures that help computers detect objects, a key technology used in self-driving cars and healthcare.

Liquid neural networks consist of “neurons” governed by equations that predict each individual neuron’s behavior over time, like most other modern model architectures.

I co-created Graph Neural Networks while at Stanford. I recognized early on that this technology was incredibly powerful.

However, current artificial neural network circuit architectures do not fully embrace small-world neural network models. Here, we present the neuromorphic Mosaic: a non-von Neumann systolic ...

The main goal of Neural Architecture is to understand how to interrogate artificial intelligence—a technological tool—in the field of architectural design, traditionally a practice that ...