Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction...

58
Introduction to Deep Learning Prof. Leal-Taixé and Prof. Niessner 1

Transcript of Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction...

Page 1: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Introduction to Deep Learning

Prof. Leal-Taixé and Prof. Niessner 1

Page 2: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

LecturersProf. Dr. Laura

Leal-TaixéProf. Dr. Matthias

Niessner

Tim Meinhardt

Tutors

The Team

JiHou

AndreasRössler

Prof. Leal-Taixé and Prof. Niessner 2

Page 3: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

What is Computer Vision?

• First defined in the 60s in artificial intelligence groups

• “Mimic the human visual system”

• Center block of robotic intelligence

Prof. Leal-Taixé and Prof. Niessner 3

Page 4: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Prof. Leal-Taixé and Prof. Niessner 4

Page 5: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Computer Vision

Some decades later…

Prof. Leal-Taixé and Prof. Niessner 5

Page 6: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Computer Vision

Physics PsychologyBiology

MathematicsEngineering Computer

scienceArtificial Intelligence

ML

Neuroscience

AlgorithmsOptimization

NLPSpeech

Robotics

OpticsImage

processing

Prof. Leal-Taixé and Prof. Niessner 6

Page 7: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Computer Vision

Physics PsychologyBiology

Engineering ComputerscienceArtificial

IntelligenceML

AlgorithmsOptimization

NLPSpeech

Robotics

OpticsImage

processing

Mathematics

Neuroscience

Prof. Leal-Taixé and Prof. Niessner 7

Page 8: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Computer Vision

Physics PsychologyBiology

Engineering ComputerscienceArtificial

IntelligenceML

AlgorithmsOptimization

NLPSpeech

Robotics

OpticsImage

processing

Mathematics

Neuroscience

Prof. Leal-Taixé and Prof. Niessner 8

Page 9: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Computer Vision

Physics PsychologyBiology

Engineering ComputerscienceArtificial

IntelligenceML

AlgorithmsOptimization

NLPSpeech

Robotics

OpticsImage

processing

Mathematics

Neuroscience

Prof. Leal-Taixé and Prof. Niessner 9

Page 10: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Pre 2012

Image classification

Prof. Leal-Taixé and Prof. Niessner 10

Page 11: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

AAwesome magic box

Become magicians Post 2012Open the box

Image classification

Prof. Leal-Taixé and Prof. Niessner 11

Page 12: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Why Deep Learning?

Prof. Leal-Taixé and Prof. Niessner 12

Page 13: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Deep Learning History

Prof. Leal-Taixé and Prof. Niessner 13

Page 14: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

The empire strikes back

Prof. Leal-Taixé and Prof. Niessner 14

Page 15: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

• MNIST digit recognition dataset

• 107 pixels used in training

• ImageNet image recognition dataset

• 1014 pixels used in training

1988LeCunet al.

2012Krizhevskyet al.

What has changed?

Prof. Leal-Taixé and Prof. Niessner 15

Page 16: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Big Data

Models know where to learn from

Hardware

Models are trainable

Deep

Models are complex

What made this possible?

Prof. Leal-Taixé and Prof. Niessner 16

Page 17: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

AlphaGo

Machine translation

Emoticon suggestion

Deep Learning nowadays

Prof. Leal-Taixé and Prof. Niessner 18

Page 18: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Self-driving cars

Deep Learning nowadays

Prof. Leal-Taixé and Prof. Niessner 19

Page 19: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Healthcare, cancer detection

Deep Learning nowadays

Prof. Leal-Taixé and Prof. Niessner 20

Page 20: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Deep Learning market

• […]market research report Deep Learning Market […] Global Forecasts to 2022", the deep learning market is expected to be worth USD 1,722.9 Million by 2022.

Prof. Leal-Taixé and Prof. Niessner 26

Page 21: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

S. Caelles, K.K. Maninis, J. Pont-Tuset, L. Leal-Taixé, D. Cremers, and L. Van Gool.One-Shot Video Object Segmentation, CVPR 2017.

Deep Learning at TUM

Prof. Leal-Taixé and Prof. Niessner 27

Page 22: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Deep Learning at TUM

Prof. Leal-Taixé and Prof. Niessner 28

Page 23: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Deep Learning at TUM

CC3

CC2

CC1

Reshape Conv+BN+ReLU Pooling Upsample Concat Score

DDFF

Prof. Leal-Taixé and Prof. Niessner 29

Page 24: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Computer Vision at TUM

ScanNet: Dai, Chang, Savva, Halber, Funkhouser, Niessner., CVPR 2017.

ScanNet Stats:-Kinect-style RGB-D sensors-1513 scans of 3D environments-2.5 Mio RGB-D frames-Dense 3D, crowd-source MTurk labels-Annotations projected to 2D frames

Prof. Leal-Taixé and Prof. Niessner 30

Page 25: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Deep Learning at TUM

Map

Photo

Prof. Leal-Taixé and Prof. Niessner 31

Page 26: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Introduction to Deep Learning

Prof. Leal-Taixé and Prof. Niessner 32

Page 27: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

About the lecture

• Theory: 12 lectures

• Every Monday 14-16h (MI HS 1)

• Practice: 3 exercises, practical sessions

• Every Thursday 8-10h (Interim HS1)

• July 2nd: guest lecture by tba

https://dvl.in.tum.de/lectures/dl4cv-ss18.htmlProf. Leal-Taixé and Prof. Niessner 33

Page 28: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Grading system

• Exam: July 16th

• Review: allow until end of July for exam reviews

• Important: no retake exam

• Practice: 4 exercises (Thursdays)

• Bonus 0.3 + questions in the final exam

https://dvl.in.tum.de/lectures/dl4cv-ss18.htmlProf. Leal-Taixé and Prof. Niessner 34

Page 29: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Exercise lectures

• Exercise 1: starting May 3rd

• Thursday lecture 1: DL math background

• Thursday lecture 2: DL math background

• Thursday lecture 3: Python introduction

Prof. Leal-Taixé and Prof. Niessner 35

Page 30: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Introduction to Deep Learning

Optimization

CNN

Introduction to NN

Machine Learning

basics

Back-propagation RNN

Prof. Leal-Taixé and Prof. Niessner 36

Page 31: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Slides• All material will be uploaded on Moodle• Questions regarding the syllabus, exercises or contents

of the lecture, use Moodle!• Questions regarding organization of the course:

• Emails to our individual addresses will not be answered.

[email protected]

Prof. Leal-Taixé and Prof. Niessner 37

Page 32: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Deep Learning at TUM

Intro to Deep

Learning

DL for Physics(Thuerey)

DL for Vision (Niessner,

Leal-Taixe)

DL for Medical Applicat.

(Menze)

DL in Robotics

(Bäuml)

Machine Learning(Günnemann)

Prof. Leal-Taixé and Prof. Niessner 38

Page 33: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Machine Learning

Prof. Leal-Taixé and Prof. Niessner 39

Page 34: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Machine learning

Task

Prof. Leal-Taixé and Prof. Niessner 40

Page 35: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Image classification

Prof. Leal-Taixé and Prof. Niessner 41

Page 36: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Pose Appearance IlluminationProf. Leal-Taixé and Prof. Niessner 42

Page 37: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Image classification

Occlusions

Prof. Leal-Taixé and Prof. Niessner 43

Page 38: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Image classification

Background clutter

Prof. Leal-Taixé and Prof. Niessner 44

Page 39: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Representation

Image classification

Prof. Leal-Taixé and Prof. Niessner 45

Page 40: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Task

Image classification

Experience

Data

Machine learning• How can we learn to perform image classification?

Prof. Leal-Taixé and Prof. Niessner 46

Page 41: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Unsupervised learning Supervised learning

Machine learning

• No label or target class

• Find out properties of the structure of the data

• Clustering (k-means, PCA)

Prof. Leal-Taixé and Prof. Niessner 47

Page 42: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Machine learning

Unsupervised learning Supervised learning

Prof. Leal-Taixé and Prof. Niessner 48

Page 43: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Machine learning

• Labels or target classes

Unsupervised learning Supervised learning

Prof. Leal-Taixé and Prof. Niessner 49

Page 44: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

DOG DOG

DOG

CAT

CAT

CAT

Machine learning

Unsupervised learning Supervised learning

Prof. Leal-Taixé and Prof. Niessner 50

Page 45: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Experience

DataTraining dataTest data

Underlying assumption that train and test data come from the same distribution

Machine learning• How can we learn to perform image classification?

Prof. Leal-Taixé and Prof. Niessner 51

Page 46: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Reinforcement learning

Agents Environmentinteraction

Machine learning

Unsupervised learning Supervised learning

Prof. Leal-Taixé and Prof. Niessner 52

Page 47: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Reinforcement learning

Agents Environmentreward

Machine learning

Unsupervised learning Supervised learning

Prof. Leal-Taixé and Prof. Niessner 53

Page 48: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

• How can we learn to perform image classification?

Task

Image classification

Experience

DataPerformance

measure

Accuracy

Machine learning

Prof. Leal-Taixé and Prof. Niessner 54

Page 49: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

A simple classifier

Prof. Leal-Taixé and Prof. Niessner 55

Page 50: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Nearest Neighbor

?Prof. Leal-Taixé and Prof. Niessner 56

Page 51: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Nearest Neighbor

distance

NN classifier = dog

Prof. Leal-Taixé and Prof. Niessner 57

Page 52: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Nearest Neighbor

distance

k-NN classifier = cat

Prof. Leal-Taixé and Prof. Niessner 58

Page 53: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Nearest Neighbor

Courtesy of Stanford course cs231n

What is the performance on training data for NN classifier?

What classifier is more likely to perform best on test data?

Prof. Leal-Taixé and Prof. Niessner 59

Page 54: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Nearest Neighbor

• Hyperparameters

• These parameters are problem dependent.

• How do we choose these hyperparameters?

Distance (L1, L2)

k (number of neighbors)

Prof. Leal-Taixé and Prof. Niessner 60

Page 55: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Cross validationtrain

validationRun 1

Run 2

Run 3

Run 4

Run 5

Split the training data into N foldsProf. Leal-Taixé and Prof. Niessner 61

Page 56: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Cross validation

train test

train testvalidation

20%

Find your hyperparameters

Prof. Leal-Taixé and Prof. Niessner 62

Page 57: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

This lecture: improving our classifier

• Beyond linear classification

• How to train complex models deep networks

• What is happening behind the scenes: optimization, CNN, regularization.

Prof. Leal-Taixé and Prof. Niessner 63

Page 58: Introduction to Deep Learning - TUM · Introduction to Deep Learning Optimization CNN Introduction to NN Machine Learning basics Back-propagation RNN Prof. Leal-Taixé and Prof. Niessner

Upcoming lecture• Next Monday: Lecture 2: Machine Learning basics

• Next Thursday: 1st practical lecture (DL math background)

Prof. Leal-Taixé and Prof. Niessner 64


E learning - Introduction

E learning - Introduction

© Negnevitsky, Pearson Education, 2005 1 Introduction Introduction Hebbian learning Hebbian learning Generalised Hebbian learning algorithm Generalised.

© Negnevitsky, Pearson Education, 2005 1 Introduction Introduction Hebbian learning Hebbian learning Generalised Hebbian learning algorithm Generalised.

What is Learning? Machine Learning: Introduction and ...pages.cs.wisc.edu/~dyer/cs540/notes/08_learning-intro.pdfMachine Learning: Introduction and Unsupervised Learning ... •Learn

What is Learning? Machine Learning: Introduction and ...pages.cs.wisc.edu/~dyer/cs540/notes/08_learning-intro.pdfMachine Learning: Introduction and Unsupervised Learning ... •Learn

LEARNING OUTCOME INTRODUCTION

LEARNING OUTCOME INTRODUCTION

Learning Objectives Introduction

Learning Objectives Introduction

Learning Organisations. Introduction Introduction Concept and Definition Concept and Definition Learning Organisation - An Active Philosophy Learning.

Learning Organisations. Introduction Introduction Concept and Definition Concept and Definition Learning Organisation - An Active Philosophy Learning.

Machine Learning Basics · Machine Learning Basics I2DL: Prof. Niessner, Prof. Leal-Taixé 1. Machine Learning Task ... Basic Recipe for Machine Learning •Split your data I2DL:

Machine Learning Basics · Machine Learning Basics I2DL: Prof. Niessner, Prof. Leal-Taixé 1. Machine Learning Task ... Basic Recipe for Machine Learning •Split your data I2DL:

Lecture 3 recap · Neural Network Credit: Li/Karpathy/Johnson 3 Prof. Leal-Taixé and Prof. Niessner. Neural Network Depth Width 4 Prof. Leal-Taixé and Prof. Niessner. Neural Network

Lecture 3 recap · Neural Network Credit: Li/Karpathy/Johnson 3 Prof. Leal-Taixé and Prof. Niessner. Neural Network Depth Width 4 Prof. Leal-Taixé and Prof. Niessner. Neural Network

Eagles learning introduction

Eagles learning introduction

Machine Learning - Introduction

Machine Learning - Introduction

An Introduction to Machine Learning - GitHub Pages · Introduction Machine learning The machine learning process What’s machine learning History Supervised learning Non-supervised

An Introduction to Machine Learning - GitHub Pages · Introduction Machine learning The machine learning process What’s machine learning History Supervised learning Non-supervised

Introduction Hebbian learning Generalised Hebbian learning algorithm Competitive learning

Introduction Hebbian learning Generalised Hebbian learning algorithm Competitive learning

CS7267 Machine Learning introduction to machine learning

CS7267 Machine Learning introduction to machine learning

Reinforcement Learning Introduction & Passive Learning

Reinforcement Learning Introduction & Passive Learning

Dhruv Madeka Introduction Theoretical Machine Learning · (learning) through experience. Theoretical Machine Learning Dhruv Madeka Introduction What is Machine Learning? Some useful

Dhruv Madeka Introduction Theoretical Machine Learning · (learning) through experience. Theoretical Machine Learning Dhruv Madeka Introduction What is Machine Learning? Some useful

Introduction to Machine Learning summaryicarus.csd.auth.gr/.../05/Introduction-to-Machine-Learning-Summary.p… · Introduction to Machine Learning General notations: • ∈ℝ :ML

Introduction to Machine Learning summaryicarus.csd.auth.gr/.../05/Introduction-to-Machine-Learning-Summary.p… · Introduction to Machine Learning General notations: • ∈ℝ :ML

Learning Layers Introduction - Informal Learning @ Work

Learning Layers Introduction - Informal Learning @ Work

Learning Introduction

Learning Introduction

Learning Curves Introduction

Learning Curves Introduction

Semisupervised Learning A brief introduction. Semisupervised Learning Introduction Types of semisupervised learning Paper for review References.

Semisupervised Learning A brief introduction. Semisupervised Learning Introduction Types of semisupervised learning Paper for review References.