Showing posts with label stanford university. Show all posts
Showing posts with label stanford university. Show all posts

Tuesday, February 14, 2023

Science of Biomechanics, Muscle Building & Recovery


The Science of Biomechanics, Muscle Building & Recovery with Dr Jordan Shallow
February 2023


Dr. Jordan Shallow is a multifaceted expert in the field of chiropractic, strength and conditioning, and performance consulting. Not only is he the founder and CEO of Prescript, but he's also the Medical Director for House of Athlete and a co-host of his own radio show.


With a background that includes being the former chiropractor at Apple world headquarters and the head strength and conditioning coach for the Stanford University Rugby team, Dr. Shallow is a force to be reckoned with. He consults with professional sports teams to integrate training and rehab models and works as a clinician and strength coach with top athletes in the NFL, NHL, and UFC.


Take a look at his Instagram, and you'll see just how incredible this man truly is. So buckle up and get ready for an enlightening conversation with one of the most intelligent performance coaches in the game.



You can follow Louisa here ---

Newsletter: https://bit.ly/3ewI5P0

Instagram: louisanicola_

Twitter : louisanicola_

YouTube: Louisa Nicola


The featured guest:

Jordan Shallow D.C (@the_muscle_doc)  Instagram



- - -

Podium is a venture fund across sports and entertainment, based in Silicon Valley.

Learn more at links.podium.vc

💌 newsletter | twitter | FB | linked-in | IG

Friday, February 10, 2023

ChatGPT and Beyond | Natural Language Understanding


ChatGPT and Beyond
Natural Language Understanding
Professor Chris Potts
Stanford University
January 2023



Chapters:
00:00 Opening 00:09 Introduction for Chris Potts 01:09 Chris Potts - Welcome to the webinar 03:43 Quick Demo of GPT-3 06:41 GLUE benchmark 10:26 How can you contribute to NLU in this era of these gargantuan models? 11:44 The last mile problem 13:35 GPT example 14:50 Contrast In-Context learning with the standard paradigm of standard supervision 16:47 What are the mechanisms behind this? 18:18 Why does this work so well? 18:35 Self-Supervision 21:08 The role of human feedback 21:32 Chat GPT Diagram 23:42 Step-by-step reasoning 28:13 LLMs for everything approach 41:29 AI Courses at Stanford 46:28 Predictions about the future


- - -

Podium is a venture fund across sports and entertainment, based in Silicon Valley.

Learn more at links.podium.vc

💌 newsletter | twitter | FB | linked-in | IG

Thursday, August 13, 2020

Vid2Player | Controllable Video Sprites that Behave and Appear like Professional Tennis Players



Would you watch Roger Federer vs Roger Federer? Serena Williams vs Roger Federer? Stanford University researchers in computer vision give you a chance to find out.

Vid2Player: Controllable Video Sprites that Behave and Appear like Professional Tennis Players

We present a system that converts annotated broadcast video of tennis matches into interactively controllable video sprites that behave and appear like professional tennis players.

Our approach is based on controllable video textures, and utilizes domain knowledge of the cyclic structure of tennis rallies to place clip transitions and accept control inputs at key decision-making moments of point play.

Most importantly, we use points from the video collection to model a player's court positioning and shot selection decisions during points.

We use these behavioral models to select video clips that reflect actions the real-life player is likely to take in a given match play situation, yielding sprites that behave realistically at the macro level of full points, not just individual tennis motions.

Our system can generate novel points between professional tennis players that resemble Wimbledon broadcasts, enabling new experiences such as the creation of matchups between players that have not competed in real life, or interactive control of players in the Wimbledon final.

According to expert tennis players, the rallies generated using our approach are significantly more realistic in terms of player behavior than video sprite methods that only consider the quality of motion transitions during video synthesis.


Research By
Haotian Zhang
Christobal Sciutto
Maneesh Agrawala
Kayvon Fathalaian
Stanford University

Learn more: https://cs.stanford.edu/~haotianz/research/vid2player/


- - -

Podium is a venture fund, accelerator and community across sports and entertainment, based in Silicon Valley.

Learn more at www.podium.vc

💌 newsletter | twitter | FB | linked-in | IG