Deep dives into AI, research, coding, and other topics.
Since its release, the public has been playing with ChatGPT and seeing what it can do, but how does ChatGPT actually work? While the details of its inner workings have not been published, we can piece together its functioning principles from recent research.
Stable Diffusion 2 was released recently, sparking some debate about its performance relative to Stable Diffusion 1. Learn where the differences between the two models stem from and what they mean in practice in this simple guide.
AlphaTensor is a novel AI solution to discover mathematical algorithms with Reinforcement Learning. Learn everything you need to know about AlphaTensor in this comprehensive introduction.
This week’s AI Research Review is Git Re-Basin: Merging Models Modulo Permutation Symmetries.
Poisson Flow Generative Models (PFGMs) are a new type of generative Deep Learning model, taking inspiration from physics much like Diffusion Models. Learn the theory behind PFGMs and how to generate images with them in this easy-to-follow guide.
This week’s AI Research Review is Multistream CNN For Robust Acoustic Modeling
This week’s AI Research Review is Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition Systems.
This week’s Deep Learning Paper Reviews is Diffusion-LM Improves Controllable Text Generation and Sparsifying Transformer Models with Trainable Representation Pooling.
Stable Diffusion is a text-to-image model with recently-released open-sourced weights. Learn how to generate an image of a scene given only a description of it in this simple tutorial.
Text-to-Image models have made great strides this year, from DALL-E 2 to the more recent Imagen model. In this tutorial learn how to build a minimal Imagen implementation - MinImagen.
This week’s Deep Learning Paper Reviews is Barlow Twins: Self-Supervised Learning via Redundancy Reduction and Sparse MoEs Meet Efficient Ensembles
This week’s Deep Learning Paper Review is Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis.
This week’s Deep Learning Paper Recaps are Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition and Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech Recognition
This week’s Deep Learning Paper Recaps are MAESTRO: Matched Speech Text Representations through Modality Matching and Masked Autoencoders that Listen.
This week’s Deep Learning Paper Recap is Prune Once For All: Sparse Pre-Trained Language Models
Given a brief description of a scene, Imagen can generate photorealistic, high-resolution images of the scene. Learn everything you need to know about Imagen and how it works in this easy-to-follow guide.
This week’s Deep Learning Paper Recaps are Bridging the gap between streaming and non-streaming ASR systems by distilling ensembles of CTC and RNN-T models and BRIO: Bringing Order to Abstractive Summarization
This week’s Deep Learning Paper Reviews are TOXIGEN: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection and Knowledge Distillation Meets Open-Set Semi-Supervised Learning.
This week’s Deep Learning Paper Review is Decision Transformer: Reinforcement Learning via Sequence Modeling and SPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training
The meteoric rise of Diffusion Models is one of the biggest developments in Machine Learning in the past several years. Learn everything you need to know about Diffusion Models in this easy-to-follow guide.
This week’s Deep Learning Paper Review is ALBERT: A Lite BERT for Self-supervised Learning of Language Representations.
This paper falls in the category of parameter efficient fine-tuning, where the goal is to use as few parameters as possible to achieve almost the same accuracy as if we were to fine-tune the whole model.
In this video, we will learn about Gradient Clipping, a technique to tackle the exploding gradients problem in Neural Networks.
Should you be using JAX in 2023? Check out our recommendations on using JAX for Deep Learning and more!
In this video, we take a high-level look on all main hyperparameters of Neural Networks.