Blogs

Parti

December 6th, 2022

Pathways Autoregressive Text-to-Image model (Parti), an autoregressive text-to-image generation model that achieves high-fidelity photorealistic image generation and supports content-rich synthesis involving complex compositions and world knowledge.

MUZERO

September 16th, 2022

A look at MuZero, the most advanced reinforcement algorithm ever.
MuZero is a reinforcement learning(RL) algorithm. RL algorithms are based on a system of rewards the machine can potentially earn for doing the right moves/actions from a particular state.

LaMDA: A Next Gen AI Model

November 29th, 2022

A family of conversational neural language models developed by Google.
LaMDA, short for Language Model for Dialogue Applications was developed by Google to have more fluent and accurate, natural conversations with people.

The Revolutionary WaveNet

September 16th, 2022

A generative model that revolutionized the world of Speech Synthesis!
WaveNet is a deep neural network that is used to produce raw sound. WaveNet was able to generate speech sounding more natural than the best existing Text-to-Speech systems, reducing the gap with human performance by over 50%.

Learning to Paint with Deep RL

March 18th, 2023

This paper decided to use model-based Deep Reinforcement Learning since it helps the model to learn using the future outcomes as well as using the history. They use a neural renderer to simulate the canvas for the model so that it can look into every possible outcome for a single action. Basically for each stroke on the canvas, the agent has to predict the stroke location, shape, stroke thickness and color.