Bridging the Gap Between Vision and Language — A Look at OpenAI’s CLIP Model — Deep learning vision models traditionally relied on vast collections of labeled images, each tailored to recognize objects in a specific category or class. OpenAI’s approach, using images and natural language, offers an alternative that doesn’t necessitate such tailored examples. They developed a CLIP model that can recognize objects without needing…

Why Can GPT Learn In-Context? Language Models Secretly Perform Gradient Descent as Meta-Optimizers — The paper Why Can GPT Learn In-Context? Language Models Secretly Perform Gradient Descent as Meta-Optimizers provides insights into how GPT-3 can learn from a few demonstrations and predict labels for unseen inputs. This ability is known as In-Context Learning (ICL). The paper explains how GPT-3 performs ICL as follows:

A Series of Video Lectures on YouTube — I’ve created a short course on deep learning with PyTorch. It contains a series of videos to cover various topics. I keep each video short and straight to the point. I hope you enjoy it! An overview of the lecture series Prerequisites to studying deep learning PyTorch Installation Tensors NumPy arrays (hands-on) PyTorch tensors (hands-on) Torchvision datasets (hands-on)

Language Models are Few-Shot Learners — #GPT #Transformer In 2020, OpenAI announced GPT-3, a generative language model with 175 billion parameters, 10x more than any previous language model, and published its performance on NLP benchmarks. However, it wasn’t just another size upgrade. GPT-3 showed the improved capability to handle tasks purely via text interaction. Those tasks…

Language Models are Unsupervised Multitask Learners — #GPT #Transformer GPT-2 is a direct scale-up of GPT-1, with more parameters and trained on more data. However, it was deemed to be too dangerous to release by OpenAI: Due to our concerns about malicious applications of the technology, we are not releasing the trained model. As an experiment in…

Generative Pre-Trained Transformer — #GPT #Transformer In 2018, OpenAI released the first version of GPT (Generative Pre-Trained Transformer) for generating texts as if humans wrote. The architecture of GPT is based on the original transformer’s decoder. They trained GPT in two stages: Unsupervised Pre-training pre-trains GPT on unlabeled text, which taps into abundant text…

The Long-Document Transformer — In 2020, researchers at Allen Institute for Artificial Intelligence (AI2) published “Longformer: The Long-Document Transformer”. AI2 is a non-profit research organization that hosts the Semantic Scholar website providing AI-driven search and discovery tools for research publications. …

Hierarchical Vision Transformer using Shifted Windows — In 2021, Microsoft announced a new Vision Transformer called Swin Transformer, which can act as a backbone for computer vision tasks like image classification, object detection, and semantic segmentation. The word Swin stands for Shifted windows that provide the Transformer with hierarchical vision, which is the main topic of this…

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale — In 2020, the Google Brain team developed Vision Transformer (ViT), an image classification model without a CNN (convolutional neural network). ViT directly applies a Transformer Encoder to sequences of image patches for classification. This article explains how ViT works. Vision Transformer Architecture Vision Transformer Overview