transformer

AI Research

GLOM: How to represent part-whole hierarchies in a neural network (Geoff Hinton’s Paper Explained)

Yannic Kilcher covers a paper where Geoffrey Hinton describes GLOM, a Computer Vision model that combines transformers, neural fields, contrastive learning, capsule networks, denoising autoencoders and RNNs. GLOM decomposes an image into a parse tree of objects and their parts. However, unlike previous systems, the parse tree is constructed dynamically and differently for each input, […]

Read More
AI Natural Language Processing

Transformers for Image Recognition at Scale

Yannic Kilcher explains why transformers are ruining convolutions. This paper, under review at ICLR, shows that given enough data, a standard Transformer can outperform Convolutional Neural Networks in image recognition tasks, which are classically tasks where CNNs excel. In this Video, I explain the architecture of the Vision Transformer (ViT), the reason why it works […]

Read More
AI Research

Explaining the Paper: Hopfield Networks is All You Need

Yannic Kilcher explains the paper “Hopfield Networks is All You Need.” Hopfield Networks are one of the classic models of biological memory networks. This paper generalizes modern Hopfield Networks to continuous states and shows that the corresponding update rule is equal to the attention mechanism used in modern Transformers. It further analyzes a pre-trained BERT […]

Read More
Generative AI Natural Language Processing

14 Cool Apps Built on OpenAI’s GPT-3 API

Bakz T. Future shows off 14 Cool applications built on top of OpenAI’s GPT-3 (general purpose transformer) API (currently in private beta). 

Read More
AI Machine Learning

Object-Centric Learning with Slot Attention

Visual scenes are often comprised of sets of independent objects. Yet, current vision models make no assumptions about the nature of the pictures they look at. Yannic Kilcher explore a paper on object-centric learning. By imposing an objectness prior, this paper a module that is able to recognize permutation-invariant sets of objects from pixels in […]

Read More
AI Natural Language Processing

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Yannic Kilcher investigates BERT and the white paper associated with it https://arxiv.org/abs/1810.04805 Abstract:We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, BERT is designed to pre-train deep bidirectional representations by jointly conditioning on both left and right context in all layers. As […]

Read More