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. Tarun Chadha
* 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
* First version, might be a bit rough, not sure if our time planning works out.
---
class: remark-slide-content-large
# About the course
* First version, might be a bit rough, not sure if our time planning works out.
* Pragmatic approach, little math.
---
class: remark-slide-content-large
# About the course
* First version, might be a bit rough, not sure if our time planning works out.
---
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).
* More about classical machine learning than about artificial neural networks.
---
class: remark-slide-content-large
# About the course (2)
* Basic concepts of Machine Learning (ML).
* More about classical machine learning than artificial neural networks.
* General overview of supervised learning and related methods.
---
class: remark-slide-content-large
# About the course (2)
* Basic concepts of Machine Learning (ML).
* More about classical machine learning than artificial neural networks.
430
431
432
433
434
435
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
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
* General overview of supervised learning and related methods.
* How to start with ML using `scikit-learn` and `Keras`.
---
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 0: Quick Introduction to numpy, pandas, matplotlib
---
class: remark-slide-content-large
# Day 1
- Chapter 0: Quick Introduction to numpy, pandas, matplotlib
- Chapter 1: General Introduction to Machine Learning
---
class: remark-slide-content-large
# Day 1
- Chapter 0: Quick Introduction to numpy, pandas, matplotlib
- Chapter 1: General Introduction to Machine Learning
- Chapter 2: Introduction to Classification
---
class: remark-slide-content-large
# Day 1
- Chapter 0: Quick Introduction to numpy, pandas, matplotlib
- 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 0: Quick Introduction to numpy, pandas, matplotlib
- 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 0: Quick Introduction to numpy, pandas, matplotlib
- 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: Classification Algorithms Overview
---
class: remark-slide-content-large
# Day 2
- Chapter 6: Pipelines and Hyperparameter Optimisation
---
class: remark-slide-content-large
# Day 2
- Chapter 6: Pipelines and Hyperparameter Optimisation
- Chapter 7: Introduction to Regression
---
class: remark-slide-content-large
# Day 2
- Chapter 6: Pipelines and Hyperparameter Optimisation
- Chapter 7: Introduction to Regression
- Chapter 8: Introduction to Neural Networks
---
class: center, middle, inverse, remark-slide-content-large
# Quick poll
---
class: remark-slide-content-large
- Jupyter Notebooks
---
class: remark-slide-content-large
- Jupyter Notebooks
- Pandas
---
class: remark-slide-content-large
- Jupyter Notebooks
- Pandas
- Matplotlib
---
class: remark-slide-content-large
- Jupyter Notebooks
- Pandas
- Matplotlib
- seaborn
---
class: remark-slide-content-large
- Jupyter Notebooks
- Pandas
- Matplotlib
- seaborn
- numpy
---
class: center, middle, inverse, remark-slide-content-large
---
class: remark-slide-content-large
# Get started
<p>1. Start Computer, choose `fedora` during startup
<br/>
<br/>
---
class: remark-slide-content-large
# Get started
<p>1. Start Computer, choose `fedora` during startup
<br/>
<br/>
<p>2. Login with your `NETHZ` credentials
<br/>
<br/>
---
class: remark-slide-content-large
# Get started
<p>1. Start Computer, choose `fedora` during startup
<br/>
<br/>
<p>2. Login with your `NETHZ` credentials
<br/>
<br/>
<p>3. Start Terminal (click `activity` top-left corner)
<br/>
<br/>
---
class: remark-slide-content-large
# Get started
<p>1. Start Computer, choose `fedora` during startup
<br/>
<br/>
<p>2. Login with your `NETHZ` credentials
<br/>
<br/>
<p>3. Start Terminal (click `activity` top-left corner)
<br/>
<br/>
<p>4. Enter <br/><br/>
<center>
<div style="font-family: Roboto Mono; font-size: .8em; color: #0069B4;">
<center>curl https://sis.id.ethz.ch/mlw/install.sh | bash</center>
</div>
</center>
<p>5. Enter <br/><br/>
<center>
<div style="font-family: Roboto Mono; font-size: .8em; color: #0069B4;">
<center>./pycharm.sh</center>
</div>
</center>
<p>4. Start Terminal (click `activity` top-left corner)
<br/>
<br/>
---
class: remark-slide-content-large
# Get started
<p>1. Start Computer, choose `fedora` during startup
<br/>
<br/>
<p>2. Login with your `NETHZ` credentials
<br/>
<br/>
<p>3. Start Terminal (click `activity` top-left corner)
<br/>
<p>4. Enter <br/><br/><div style="font-family: Roboto Mono; font-size: .8em; color: #0069B4;"><center>curl https://sis.id.ethz.ch/mlw/install.sh | bash</center></div>
<p>5. Wait and press `ENTER` when asked
---
class: remark-slide-content-large
# Get started
<p>1. Start Computer, choose `fedora` during startup
<br/>
<br/>
<p>2. Login with your `NETHZ` credentials
<br/>
<br/>
<p>3. Start Terminal (click `activity` top-left corner)
<br/>
<br/>
<p>4. Enter <br/><br/><div style="font-family: Roboto Mono; font-size: .8em; color: #0069B4;"><center>curl https://sis.id.ethz.ch/mlw/install.sh | bash</center></div>
<p>5. Wait and press `ENTER` when asked.
<br/>
<br/>
<p>6. <strong>Don't switch of / shutdown the computer during the two days !</strong>
---
class: remark-slide-content-large
## How to upload the notebooks to polybox
<p>1. Start Terminal (click `activity` top-left corner)
<br/>
<br/>
<p>2. Enter <br/><br/><div style="font-family: Roboto Mono; font-size: .8em; color: #0069B4;"><center>ln -s .tmp/ml_workshop $HOME</center></div>
<br/>
<p>3. You should find the notebooks in `ml_workshop` in your homefolder.
<br/>
.
<p>4. Open `https://polybox.ethz.ch` to upload your notebooks manually .
<br/>
---