Topology of Artificial Neuron Activations in Deep Learning

Explore the topology of artificial neuron activations in deep learning, from image classification to natural language processing, in this comprehensive lecture. Delve into the intricacies of deep convolutional neural networks like GoogLeNet and ResNet, as well as transformer-based language models such as BERT and its variants. Gain insights into recent research efforts aimed at understanding the topological structures underlying artificial neuron activations across different domains of deep learning. Learn how these topological perspectives can shed light on the inner workings of complex neural networks and potentially inform future advancements in both computer vision and natural language processing tasks.

Bei Wang (4/18/23): Topology of Artificial Neuron Activations in Deep Learning