Revenge of the Perceptrons

Revenge of the Perceptrons

Why use a complex model when a simple one will do? New work shows that the simplest multilayer neural network, with a small twist, can perform some tasks as well as today’s most sophisticated architectures.

What’s new: Ilya Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, and a team at Google Brain revisited multilayer perceptrons (MLPs, also known as vanilla neural networks). They built MLP-Mixer, a no-frills model that approaches state-of-the-art performance in ImageNet classification.

Why it matters: MLPs are the simplest building blocks of deep learning, yet this work shows they can match the best-performing architectures for image classification.

We’re thinking: If simple neural nets work as well as more complex ones for computer vision, maybe it’s time to rethink architectural approaches in other areas, too.

To read full story, click HERE