MAMBA + SSMs: Introduction and Overview

In this multi-part series, our Head of AI, Aaron McClendon, and Lead Data Scientist, Juan Morinelli, walk through some of the key elements in a type of sequence modeling known as state space modeling (SSM).

The goal of this first webinar is to provide a theoretical primer of the state space modeling core of the Mamba architecture.

Who should watch this?

Any technical folks looking to stay up to date on language modeling techniques and expand their development skillset.

Mamba is useful for RAG systems with long corporate docs and forms a viable alternative to the transformer architecture that makes up much of modern language models (like ChatGPT and Claude).

Additional Resources:

• Mamba: Linear-Time Sequence Modeling with Selective State Spaces (https://arxiv.org/abs/2312.00752)
• Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality (https://arxiv.org/abs/2405.21060)

Join Aaron and Juan as they dive into the theory around Mamba 1 and be sure to keep an eye out for our future videos in this series.