Overview
Explore deep learning frameworks in this 41-minute talk by Peter Morgan at the ODSC London Meet-up. Gain insights from a computer science industry veteran with over 15 years of experience and a background in high-energy physics. Delve into the history and current state of deep learning, covering topics such as multilayer perception, activation functions, overfitting, and various deep learning algorithms. Learn about cutting-edge developments from industry leaders like DeepMind, Google, and Facebook, and discover open-source tools for implementing deep learning solutions. Enhance your understanding of neural networks, including feedforward networks, support vector machines, and recurrent neural networks. Perfect for data scientists and AI enthusiasts looking to expand their knowledge of deep learning frameworks and their practical applications.
Syllabus
Introduction
Agenda
Disclaimer
The Big Picture
What is Deep Learning
History of Deep Learning
Today 2016
Data sets
Selfawareness
Multilayer perception
Layers and nodes
Connections
Activation Function
Softmax Function
Overfitting
Feedforward Network
Support Vector Machine
Deep Learning Algorithms
Backpropagation
Markov Models
Restricted Boltzmann Machines
Recurrent Neural Networks
State of the Art
Deep Mind
Open Source
Google
Facebook
Theano
Questions
Taught by
Open Data Science