Newer
Older
<!DOCTYPE html>
<html>
<head>
<title>Title</title>
<meta charset="utf-8">
<style>
@import url(https://fonts.googleapis.com/css?family=Yanone+Kaffeesatz);
@import url(https://fonts.googleapis.com/css?family=Droid+Serif:400,700,400italic);
@import url(https://fonts.googleapis.com/css?family=Ubuntu+Mono:400,700,400italic);
@import url(https://fonts.googleapis.com/css?family=Abel:400,700,400italic);
@import url(https://fonts.googleapis.com/css?family=Ropa+Sans:400,700,400italic);
@import url(https://fonts.googleapis.com/css?family=Cabin:400,700,400italic);
@import url(https://fonts.googleapis.com/css?family=Roboto+Mono:400,700,400italic);
body { font-family: 'Arial'; font-size: 200%; color: #404040;}
font-family: 'Cabin';
font-weight: 400;
color: #1F407A;
}
.remark-frontslide-content { padding: 0; border: 10 px solid blue; }
.remark-slide-content-large { font-size: 90%; }
.remark-slide { border: 10 px solid blue; }
.remark-slide-content h1 { font-size: 3em; }
.remark-slide-content h2 { font-size: 2em; }
.remark-slide-content h3 { font-size: 1.6em; }
.remark-slide-content h4 { font-size: 1.2em; }
.remark-slide-content-large h1 { font-size: 2em; }
.remark-slide-content-large h2 { font-size: 1.6em; }
.footnote {
position: absolute;
bottom: 3em;
}
p {
display: block;
-webkit-margin-before: 0em;
-webkit-margin-after: 0em;
-webkit-margin-start: 0px;
}
-
li p { line-height: 1.25em; }
.red { color: #fa0000; }
.large { font-size: 2em; }
a, a > code {
}
.inverse {
background: #1F407A;
color: #777872;
text-shadow: 0 0 20px #333;
}
.inverse h1, .inverse h2 {
color: #f3f3f3;
line-height: 0.8em;
}
code {
-moz-border-radius: 5px;
-web-border-radius: 5px;
border-radius: 5px;
}
.remark-code, .remark-inline-code { font-family: 'Ubuntu Mono'; }
.remark-code-line-highlighted { background-color: #473832; }
.pull-left {
float: left;
width: 47%;
}
.pull-right {
float: right;
width: 47%;
}
.pull-right ~ p {
clear: both;
}
#slideshow .slide .content code {
font-size: 0.8em;
}
#slideshow .slide .content pre code {
font-size: 0.9em;
padding: 15px;
}
strong {
.remark-code, .remark-inline-code { font-family: 'Roboto Mono';}
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
</style>
</head>
<body>
<textarea id="source">
class: inverse, center, middle, remark-frontslide-content
<img src="./front_page.png" width=100%/>
---
class: center, middle, inverse, remark-slide-content-large
# About us
---
class: remark-slide-content-large
## About Scientific IT Services (SIS)
---
class: remark-slide-content-large
## About Scientific IT Services (SIS)
- IT Services close to research
- Zoo of experts with diverse background
---
class: remark-slide-content-large
## About Scientific IT Services (SIS)
- IT Services close to research
- Zoo of experts with diverse background
#### Here today in real:
* Dr. Mikolaj Rybinski
* Dr. Uwe Schmitt
---
class: remark-slide-content-large
- Scientific Computing Services: Euler, ...
---
class: remark-slide-content-large
- Scientific Computing Services: Euler, ...
- Data Science Support
---
class: remark-slide-content-large
- Scientific Computing Services: Euler, ...
- Data Science Support
---
class: remark-slide-content-large
- Scientific Computing Services: Euler, ...
- Data Science Support
- Scientific Visualization
---
class: remark-slide-content-large
- Scientific Computing Services: Euler, ...
- Data Science Support
- Scientific Visualization
- Consulting and Training: Code Clinics, ...
---
class: remark-slide-content-large
- Scientific Computing Services: Euler, ...
- Data Science Support
- Scientific Visualization
- Consulting and Training: Code Clinics, ...
- Research Data Management
---
class: remark-slide-content-large
- Scientific Computing Services: Euler, ...
- Data Science Support
- Scientific Visualization
- Consulting and Training: Code Clinics, ...
- Research Data Management
- Research Data Analysis
---
class: remark-slide-content-large
- Scientific Computing Services: Euler, ...
- Data Science Support
- Scientific Visualization
- Consulting and Training: Code Clinics, ...
- Research Data Management
- Research Data Analysis
- Personalized Health Data Services
---
class: center, middle, remark-slide-content-large
<span style="font-size: 180%; color: #1F407A;">
We also offer data science support,
<br/>
so don't hesitate to
<br/>
contact us...
<br/>
<br/>
https://sis.id.ethz.ch/
</span>
---
class: center, middle, inverse, remark-slide-content-large
# About the course
---
class: remark-slide-content-large
# About the course
---
class: remark-slide-content-large
# About the course
* Pragmatic approach, little math.
---
class: remark-slide-content-large
# About the course
---
class: remark-slide-content-large
# About the course (2)
* Basic concepts of Machine Learning (ML).
---
class: remark-slide-content-large
# About the course (2)
* Basic concepts of Machine Learning (ML).
* We start with classical ML using `scikit-learn`.
---
class: remark-slide-content-large
# About the course (2)
* Basic concepts of Machine Learning (ML).
* We start with classical ML using `scikit-learn`.
* General overview of supervised learning and related methods.
---
class: remark-slide-content-large
# About the course (2)
* Basic concepts of Machine Learning (ML).
* We start with classical ML using `scikit-learn`.
* General overview of supervised learning and related methods.
* Introduction to concepts of deep learning using `Keras`.
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
---
class: remark-slide-content-large
# About the course (3)
What will you NOT learn?
* How to program with Python.
---
class: remark-slide-content-large
# About the course (3)
What will you NOT learn?
* How to program with Python.
* How exactly ML methods work.
---
class: remark-slide-content-large
# About the course (3)
What will you NOT learn?
* How to program with Python.
* How exactly ML methods work.
* Unsupervised learning methods.
---
class: center, middle, inverse, remark-slide-content-large
# Schedule
---
class: remark-slide-content-large
# Day 1
- Chapter 1: General Introduction to Machine Learning
---
class: remark-slide-content-large
# Day 1
- Chapter 1: General Introduction to Machine Learning
- Chapter 2: Introduction to Classification
---
class: remark-slide-content-large
# Day 1
- Chapter 1: General Introduction to Machine Learning
- Chapter 2: Introduction to Classification
- Chapter 3: Overfitting and Cross Validation
---
class: remark-slide-content-large
# Day 1
- Chapter 1: General Introduction to Machine Learning
- Chapter 2: Introduction to Classification
- Chapter 3: Overfitting and Cross Validation
- Chapter 4: Measuring Quality of a Classifier
---
class: remark-slide-content-large
# Day 1
- Chapter 1: General Introduction to Machine Learning
- Chapter 2: Introduction to Classification
- Chapter 3: Overfitting and Cross Validation
- Chapter 4: Measuring Quality of a Classifier
- Chapter 5: Pipelines and Hyperparameter Optimisation
---
class: remark-slide-content-large
# Day 1
- Chapter 1: General Introduction to Machine Learning
- Chapter 2: Introduction to Classification
- Chapter 3: Overfitting and Cross Validation
- Chapter 4: Measuring Quality of a Classifier
- Chapter 5: Pipelines and Hyperparameter Optimisation
- Chapter 6A: Classification Algorithms Overview
---
class: remark-slide-content-large
# Day 2
---
class: remark-slide-content-large
# Day 2
- Chapter 6B: Classification Algorithms Overview
- Chapter 7: Introduction to Regression
---
class: remark-slide-content-large
# Day 2
- Chapter 7: Introduction to Regression
- Chapter 8: Introduction to Neural Networks
---
class: remark-slide-content-large
- Real world example: Using EEG data to predict hand movements
- Real world example: Using EEG data to predict hand movements
- Real world example: Using Deep learning to detect tumor in images.
- Real world example: Using EEG data to predict hand movements
- Real world example: Using Deep learning to detect tumor in images.
- You work on your own data or on a data set we provided.
- We have exercise sections during the script where you will work on your own.
- We have exercise sections during the script where you will work on your own.
- We have exercise sections during the script where you will work on your own.
- We also have optional exercises if you get bored.
---
class: center, middle, inverse, remark-slide-content-large
---
class: remark-slide-content-large
---
class: remark-slide-content-large
- seaborn
- numpy
---
class: center, middle, inverse, remark-slide-content-large
# Questions?
---
class: remark-slide-content-large
## Get started
Please follow **carefully** the instructions from the printout.