Scribd
Upload
146 views37 pages

Fundamentals of Deep Learning

This document provides an overview and agenda for an introductory course on deep learning. The course aims to quickly get students up and running with deep learning and provide a foundation to tackle projects. The agenda covers the history of AI, the deep learning revolution enabled by data and computing power, what deep learning is and how it is transforming different domains. It also outlines hands-on exercises, the structure of the course and software/platform used. The first exercise involves training a network to classify handwritten digits.

Uploaded by

AlejandroHerreraGurideChile
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
146 views37 pages

Fundamentals of Deep Learning

This document provides an overview and agenda for an introductory course on deep learning. The course aims to quickly get students up and running with deep learning and provide a foundation to tackle projects. The agenda covers the history of AI, the deep learning revolution enabled by data and computing power, what deep learning is and how it is transforming different domains. It also outlines hands-on exercises, the structure of the course and software/platform used. The first exercise involves training a network to classify handwritten digits.

Uploaded by

AlejandroHerreraGurideChile
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 37

FUNDAMENTALS OF

DEEP LEARNING
Part 1: An Introduction to Deep Learning

1
WELCOME!
2
THE GOALS OF THIS COURSE

• Get you up and on your feet quickly


• Build a foundation to tackle a deep learning project right away
• We won’t cover the whole field, but we’ll get a great head start
• Foundation from which to read articles, follow tutorials, take further
classes
Part 1: An Introduction to Deep Learning

Part 2: How a Neural Network Trains

AGENDA Part 3: Convolutional Neural Networks

Part 4: Data Augmentation and Deployment

Part 5: Pre-trained Models

Part 6: Advanced Architectures


AGENDA – PART 1
• History of AI
• The Deep Learning Revolution
• What is Deep Learning
• How Deep Learning is Transforming the World
• Overview of the Course
• First Exercise
LET’S GET STARTED

8
HISTORY OF AI
9
BEGINNING OF ARTIFICIAL INTELLIGENCE

COMPUTERS ARE MADE IN EARLY ON, GENERALIZED TURNED OUT TO BE HARDER


PART TO COMPLETE HUMAN INTELLIGENCE LOOKED THAN EXPECTED
TASKS POSSIBLE

10
EARLY NEURAL NETWORKS

Inspired by biology

Created in the 1950’s

Outclassed by Von
Neumann Architecture

11
EXPERT SYSTEMS

Highly complex

Programmed by hundreds of engineers

Rigorous programming of many rules


EXPERT SYSTEMS - LIMITATIONS

What are these three images?

13
HOW DO CHILDREN LEARN?

• Expose them to lots of data


• Give them the “correct
answer”
• They will pick up the
important patterns on their
own

14
THE DEEP LEARNING
REVOLUTION
15
DATA

- Networks need a lot of


information to learn from
- The digital era and the
internet has supplied that
data

16
COMPUTING POWER
Need a way for our artificial “brain” to observe lots of data
within a practical amount of time.

17
THE IMPORTANCE OF THE GPU

A Rendered Image A Neural Network

18
WHAT IS DEEP LEARNING?
19
DEEP LEARNING FLIPS TRADITIONAL
PROGRAMMING ON ITS HEAD

20
TRADITIONAL PROGRAMMING
Building a Classifier

1 2 3
Define a set of Program those Feed it examples,
rules for rules into the and the program
classification computer uses the rules to
classify
MACHINE LEARNING
Building a Classifier

1 2 3
Show model the Model takes Model learns to
examples with the guesses, we tell it correctly
answer of how to if it’s right or not categorize as it’s
classify training. The
system learns the
rules on its own
THIS IS A FUNDAMENTAL SHIFT
WHEN TO CHOOSE DEEP LEARNING

Classic Programming Deep Learning

If rules are clear


If rules are
and
nuanced, complex,
straightforward,
difficult to discern,
often better to just
use deep learning
program it
24
DEEP LEARNING COMPARED TO OTHER AI

Depth and complexity of networks

Up to billions of parameters (and growing)

Many layers in a model

Important for learning complex rules


HOW DEEP LEARNING IS
TRANSFORMING THE WORLD
26
COMPUTER VISION

ROBOTICS AND OBJECT SELF DRIVING


MANUFACTURING DETECTION CARS

27
NATURAL LANGUAGE PROCESSING

REAL TIME VOICE VIRTUAL


TRANSLATION RECOGNITION ASSISTANTS

28
RECOMMENDER SYSTEMS

CONTENT TARGETED SHOPPING


CURATION ADVERTISING RECOMMENDATIONS

29
REINFORCEMENT LEARNING

ALPHAGO BEATS AI BOTS BEAT STOCK TRADING


WORLD CHAMPION PROFESSIONAL ROBOTS
IN GO VIDEOGAMERS
30
OVERVIEW OF THE
COURSE
31
HANDS ON EXERCISES

• Get comfortable with the


process of deep learning
• Exposure to different models
and datatypes
• Get a jump-start to tackle
your own projects

32
STRUCTURE OF THE COURSE
“Hello World” of Deep Learning

Train a more complicated model

New architectures and techniques to improve


performance

Pre-trained models

Transfer learning
33
PLATFORM OF THE COURSE

GPU powered cloud server

JupyterLab platform

Jupyter notebooks for interactive coding


SOFTWARE OF THE COURSE

• Major deep learning platforms:


• TensorFlow + Keras (Google)
• Pytorch (Facebook)
• MXNet (Microsoft)
• We’ll be using TensorFlow and Keras
• Good idea to gain exposure to others
moving forward

35
FIRST EXERCISE:
CLASSIFY HANDWRITTEN
DIGITS
36
HELLO NEURAL NETWORKS

Train a network to • Historically important and


correctly classify
handwritten digits difficult task for computers

• Get exposed to the example, and


Try learning like a
Neural Network try to figure out the rules to how
it works

37
LET’S GO!

38
39

You might also like