Computer Visions | GenAI Speaker Series

This speaker series presents an immersive exploration into the world of generative AI, showcasing its application in activities such as impressionist painting, music composition, prose writing, coding, and conversational interaction. Attendees will engage with generative AI models and learn through practical demonstrations. The series will feature talks and workshops led by real artists, professionals, entrepreneurs, educators, and researchers, offering insights into AI’s practical applications and generation techniques. It aims to demystify how AI models generate content in various media including text, code, speech, music, and images. Designed for those new to AI as well as advanced learners, the series provides a comprehensive overview of the latest generative AI methods and encourages participants to apply these tools in their own fields of interest.

Fall’22 Speakers (class page) include: Emad Mostaque (Founder @ Stability AI), David Ha (Founder @ Sakana AI), Poli Passos (🤗).

Host: Dr. Roy Shilkrot

Fall’23 Speakers

We will host a number of speakers from the world of generative media, all active artists, researchers and leaders that will share the actual methods they use for their work (including links to code and examples).

Prof. Ethan Mollick

Associate Professor at The Wharton School, University of Pennsylvania
Guillermo Rauch

Co-Founder and CEO at Vercel
Lior Sinclair

AI Eduactor, ML Engineer/Researcher, Founder AlphaSignal.ai
Akshay Pachaar

Lead Data Scientist at TomTom
Jonathan Whitaker

Data scientist and AI researcher
Prof. Dan Novy

Assistant Professor of Emerging Media Arts at the University of Nebraska-Lincoln
Rinon Gal

PhD Student at TAU Graphics, GenAI Researcher at Nvidia
Doron Adler

Software engineer, GenAI artist and engineer
Pat Pataranutaporn

PhD Candidate at MIT, GenAI researcher
Santiago Valdarrama

ML educator and GenAI engineer

MAS.S63 Fall 2023

The class portion of Computer Visions is open for student registrations for Fall’23.

Location: E15-359 (some sessions will be remote)
Time: Mondays, 4-6pm
Instructors: Dr. Roy Shilkrot, Prof. Pattie Maes
Units: 0-6-0

Topics Covered

  • Students with use online materials to get familiar with the mechanics and concepts in Machine Learning and Deep Learning (model, classification, regression, supervision, train-test, loss, overfitting, regularization, linear models, neural nets, back-propagation optimization, convolution, recurrence, attention, transformers). While it will be mentioned in class, we will not cover them in depth.
  • Working environments for generative media, e.g. Google Colab, Jupyter Notebooks, Streamlit/Gradio APIs, Hugginface Spaces, etc.
  • Significant ML models and architectures of interest: GANs (pix2pixX, Style), Diffusion Models (e.g. Stable), LLMs (GPT-n, llama-n, etc.), Speech (SeamlessM4T, Whisper), Music & Audio (MuseFormer, AudioCraft, AudioLDM), and more.