Probabilistic Programming in Python

Overview

Explore probabilistic programming in Python through this EuroPython 2014 conference talk by Thomas Wiecki. Gain insights into Bayesian statistics and learn how to specify and estimate probabilistic models using PyMC3. Discover the power of next-generation sampling algorithms, intuitive model specification syntax, and just-in-time compilation for efficient large-scale probabilistic modeling. Delve into topics such as machine learning, simulation, maximum likelihood estimation, Markov Chain Monte Carlo sampling, and hierarchical models. Understand how probabilistic programming can be applied across various scientific fields, including cognitive science, data science, and quantitative finance.

Syllabus

Introduction
Machine Learning
Open Box
Be Testing
Simulation
Maximum likelihood estimate
Frequent of Statistics
Based Formula
Random Variable
Chain Monte Carlo
MCMC Sampling
High MC3
Uncooled Model
Fully Pooled Model
Partially Hierarchical Model
PartialHierarchical Model