Talk: Colin Carroll - Getting started with automatic differentiation
Presented by:
Colin Carroll
The derivative is a concept from calculus which gives you the rate of change of a function: for a small change in an input, how much does the output change? This idea turns out to be very important in natural sciences, and is used in many optimization algorithms, which find the maximum or minimum of functions.
Automatic differentiation is a technique for computing the derivative of a function. Python has a number of libraries implementing automatic differentiation, many of which are put to use for deep learning, but can be used on their own.
In this talk I will give intuition for the derivative and its high dimensional sibling, the gradient. We will take a tour of applications, including optimization and computational art, with examples using jax, TensorFlow, and PyTorch. We conclude with a brief description of alternative ways of computing derivatives in Python, and their relative strengths.
Видео Talk: Colin Carroll - Getting started with automatic differentiation канала PyCon US
Colin Carroll
The derivative is a concept from calculus which gives you the rate of change of a function: for a small change in an input, how much does the output change? This idea turns out to be very important in natural sciences, and is used in many optimization algorithms, which find the maximum or minimum of functions.
Automatic differentiation is a technique for computing the derivative of a function. Python has a number of libraries implementing automatic differentiation, many of which are put to use for deep learning, but can be used on their own.
In this talk I will give intuition for the derivative and its high dimensional sibling, the gradient. We will take a tour of applications, including optimization and computational art, with examples using jax, TensorFlow, and PyTorch. We conclude with a brief description of alternative ways of computing derivatives in Python, and their relative strengths.
Видео Talk: Colin Carroll - Getting started with automatic differentiation канала PyCon US
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Talks - Michael Droettboom: Measuring the performance of CPythonTutorial: Andrew Knight - Hands-On Web App Test AutomationTALK / Josh Izaac / What are quantum computers, and how can we train them in Python?Tutorial - Pradeep Kumar Srinivasan, Jia Chen, Shannon Zhu: Python Types for Fun and ProfitCharlas - Laura Gutiérrez Funderburk: Reduciendo prejuicio en la inteligencia artificial...SPONSOR WORKSHOP / Shay DeWael and Alissa Renz /SlackCharlas - María Andrea Vignau: Bailo con tu sombra: Patch, stub, mockTalk - Joseph Lucas: Serialization More than picklingTutorials - Pavithra, Andrew, Dharhas: From RAGs to riches: Build an AI document inquiry web-appTalks - Valerio Maggio: Pythonic `functional` (`iter`)tools for your data challengesTALK / James Murphy / From 3 to 300 fps: NES Emulation in Python and CythonTutorials - Aya Elsayed, Rhythm Patel: No More Raw SQL: SQLAlchemy, ORMs & asyncioTalk: Rebeca Sarai - Privacy-preserving methods: Building secure projectsSponsor Presentation - Fixing legacy code, one pull request at a timeTalks - Kevin Kho, Han Wang: Speed is Not All You Need for Data ProcessingTalks - Dan Craig: Testing Spacecraft with PytestPython Steering Council Community AddressTutorials - Kevin Lacaille, Mansi Shah: Eroding Coastlines: A Geospatial & Computer Vision AnalysisMeet our Keynote Speakers: Simon WillisonCharlas - Luis Conejo: De cero a 200 OK en 30 minutos Desarrollo Web con Django, Heroku...Charlas - Marina Moro López: Biohacking con Python: cómo convertirse en el señor Burns fluorescente