![Page 1: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/1.jpg)
Applied Machine LearningLecture 10: Unsupervised learning
Selpi ([email protected])
The slides are further development of Richard Johansson's slides
February 25, 2020
![Page 2: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/2.jpg)
Overview
Di�erent learning approaches
Unsupervised learning
Clustering
modeling distributions
dimensionality reduction
![Page 3: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/3.jpg)
Di�erent learning approaches based on supervision
![Page 4: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/4.jpg)
Di�erent learning approaches based on supervision
![Page 5: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/5.jpg)
Di�erent learning approaches based on supervision
![Page 6: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/6.jpg)
Overview
Di�erent learning approaches
Unsupervised learning
Clustering
modeling distributions
dimensionality reduction
![Page 7: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/7.jpg)
Unsupervised learning
I Why do this?I hand-labeled data might not be available or expensive and
time-consuming to produce
I Goal:I to discover structure in the data to summarise, explore,
visualise, and understand data
![Page 8: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/8.jpg)
Applications of unsupervised learning
![Page 9: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/9.jpg)
Main types of unsupervised approaches
I grouping the data: clustering
I modeling the statistical distribution of the data
I dimensionality reduction: projecting a high-dimensional
dataset to a lower dimensionality
![Page 10: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/10.jpg)
Overview
Di�erent learning approaches
Unsupervised learning
Clustering
modeling distributions
dimensionality reduction
![Page 11: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/11.jpg)
clustering
I clustering describes the data by forming groups (partitions)or hierarchies
5 4 3 2 1 0 1 2
3
2
1
0
1
2
3
lv et fi lt mt pl cs sk sl ro en fr it es pt hude nl da sv0.0
2.5
5.0
7.5
10.0
12.5
15.0
17.5
![Page 12: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/12.jpg)
What do we need to be able to cluster data?
I Euclidean distanceI Manhattan distance
![Page 13: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/13.jpg)
Di�erent clustering methods
I PartitionalI K-meansI Graph-basedI EM
I HierarchicalI Single linkageI Average linkageI Median linkageI Complete linkageI Centrod linkageI Ward's method
I ...
I Neural network
![Page 14: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/14.jpg)
in scikit-learn
http://scikit-learn.org/stable/modules/clustering.html
![Page 15: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/15.jpg)
�at clustering
4 2 0 2 4 6 8 100
2
4
6
8
10
6 4 2 0 2 4 6 8
8
6
4
2
0
2
4
6
![Page 16: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/16.jpg)
�at clustering methods: overview
![Page 17: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/17.jpg)
K-means (1)
I each cluster is represented by its
centroid µi
I minimize the within-cluster sum
of squares:
argminS
k∑i=1
∑x∈Si
‖x− µi‖2
Randomly initialise k cluster centroids
repeat until converged:assign cluster to each training data, based on distance
move each centroid to the centre of its cluster
![Page 18: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/18.jpg)
K-means (2)
I How to determine number of clusters?I Elbow method, trial and error, use domain knowledge
I AdvantagesI simple, easy to understand, fast, robust enough, good for
distinct clusters
I DisadvantagesI Rely on k, can have local minima, depends on initialisation, it
clusters even a uniform data, cannot handle outlier, sensitiveto scalling
I See Demo!
![Page 19: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/19.jpg)
K-means (2)
I How to determine number of clusters?I Elbow method, trial and error, use domain knowledge
I AdvantagesI simple, easy to understand, fast, robust enough, good for
distinct clusters
I DisadvantagesI Rely on k, can have local minima, depends on initialisation, it
clusters even a uniform data, cannot handle outlier, sensitiveto scalling
I See Demo!
![Page 20: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/20.jpg)
K-means (2)
I How to determine number of clusters?I Elbow method, trial and error, use domain knowledge
I AdvantagesI simple, easy to understand, fast, robust enough, good for
distinct clusters
I DisadvantagesI Rely on k, can have local minima, depends on initialisation, it
clusters even a uniform data, cannot handle outlier, sensitiveto scalling
I See Demo!
![Page 21: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/21.jpg)
K-means (2)
I How to determine number of clusters?I Elbow method, trial and error, use domain knowledge
I AdvantagesI simple, easy to understand, fast, robust enough, good for
distinct clusters
I DisadvantagesI Rely on k, can have local minima, depends on initialisation, it
clusters even a uniform data, cannot handle outlier, sensitiveto scalling
I See Demo!
![Page 22: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/22.jpg)
DBSCAN
[source]
Parameters: eps and min_samples
1) Randomly select a point P
2) Retrieve all points directly density-reachable from P w.r.t. eps
(radius to search for neighboors).
- If P is a core point, a cluster is formed. Find recursively all its
density conected points and assign them to the same cluster as P
- If P is not a core point, iterate through the remaining unvisited
points in the dataset
![Page 23: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/23.jpg)
DBSCAN example
6 4 2 0 2 4 6 8
8
6
4
2
0
2
4
6
See demo!
![Page 24: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/24.jpg)
Discussion
I why is clustering hard?
I Di�cult to interpret and evaluate the results
![Page 25: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/25.jpg)
Discussion
I why is clustering hard?I Di�cult to interpret and evaluate the results
![Page 26: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/26.jpg)
Evaluating clustering algorithms
I how could we evaluate the result produced by a clusteringalgorithm?I Check Silhouette scoreI Compare with gold standard data (if any)
![Page 27: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/27.jpg)
Evaluating �at clustering (1): internal consistency
5 4 3 2 1 0 1 2
3
2
1
0
1
2
3
5 4 3 2 1 0 1 2
3
2
1
0
1
2
3
![Page 28: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/28.jpg)
Cluster evaluation: the silhouette score
I Measures how close each object is to its own cluster compared
to other clusters.
I For each data point xi , the silhouette score is de�ned
si =bi − ai
max(ai , bi )
whereI ai is the average distance to other members in the same
clusterI bi the minimal average distance to another cluster
I then we take the average over all the data
I in scikit-learn: sklearn.metrics.silhouette_score
![Page 29: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/29.jpg)
example
5 4 3 2 1 0 1 2
3
2
1
0
1
2
3
silhouette = 0.68
5 4 3 2 1 0 1 2
3
2
1
0
1
2
3
silhouette = 0.42
![Page 30: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/30.jpg)
evaluating �at clustering (2): comparing to a gold standard
![Page 31: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/31.jpg)
evaluating �at clustering (2): comparing to a gold standard
I scikit-learn contains several evaluation metrics for this scenarioI http://scikit-learn.org/stable/modules/classes.
html#clustering-metricsI http://scikit-learn.org/stable/modules/clustering.
html#clustering-evaluation
I for instance, the adjusted Rand score:
[source]
![Page 32: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/32.jpg)
hierarchical clustering
See demo!
![Page 33: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/33.jpg)
Single linkage clustering
[source]
![Page 34: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/34.jpg)
Complete linkage clustering
[source]
![Page 36: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/36.jpg)
Overview
Di�erent learning approaches
Unsupervised learning
Clustering
modeling distributions
dimensionality reduction
![Page 37: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/37.jpg)
modeling distributions
I we are given a dataset and now we need toI visualize the distributionI �nd the most probable region in the dataI randomly generate new synthetic data from
the same distributionI are there any exceptional data points?I for some new data point x, does it seem
plausible that it comes from the samedistribution?
[source]
I we need to model the statistical distribution of the dataI how would we solve this using an approach we've seen in a
basic stats class?I . . . and what are the limitations of that method?
![Page 38: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/38.jpg)
modeling distributions
I we are given a dataset and now we need toI visualize the distributionI �nd the most probable region in the dataI randomly generate new synthetic data from
the same distributionI are there any exceptional data points?I for some new data point x, does it seem
plausible that it comes from the samedistribution?
[source]
I we need to model the statistical distribution of the dataI how would we solve this using an approach we've seen in a
basic stats class?I . . . and what are the limitations of that method?
![Page 39: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/39.jpg)
kernel density estimation
[source]
![Page 41: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/41.jpg)
in scikit-learn
sklearn.neighbors.KernelDensity
![Page 43: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/43.jpg)
novelty detection, anomaly detection, . . .
[source]
Applications: fraud detection, cyber security, manufacturing
processes, monitoring machine.
![Page 44: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/44.jpg)
Anomaly detection vs supervised
I Anomaly detection: Very small number of positive examples,
large number of negative examples, future anomalies are
unlikely to be similar to the training set
I Supervised: Large number of positives and negatives future
examples are likely to be similar to training set.
![Page 45: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/45.jpg)
in scikit-learn
http://scikit-learn.org/stable/modules/outlier_
detection.html
![Page 46: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/46.jpg)
one-class SVM
I the one-class SVM tries to �nd a decision boundary that
encloses the training data (except a fraction ν)
[source]I it can be used for novelty and outlier detection
![Page 47: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/47.jpg)
one-class SVM (formally)
![Page 48: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/48.jpg)
Anomaly detection - choosing features
I Plot histogram of data, see if the data looks gaussian. If not
gaussian, do transformation to make the data look gaussian
(e.g., take log(x) and plot the data again).
I log(x) can be changed with other function. The function that
makes the data more Gaussian can be used as a feature
![Page 49: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/49.jpg)
evaluation of anomaly detection systems
I how do you think it should be done?
![Page 50: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/50.jpg)
Overview
Di�erent learning approaches
Unsupervised learning
Clustering
modeling distributions
dimensionality reduction
![Page 51: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/51.jpg)
dimensionality reduction
I reducing a high-dimensional dataset to a low-dimensional one
I why?I visualizing, understandingI reducing the need for storageI making supervised/unsupervised algorithms run fasterI making supervised/unsupervised learning easier
![Page 52: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/52.jpg)
Principal Component Analysis
[source]
![Page 53: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/53.jpg)
autoencoders: dimensionality reduction using a NN
I for several Keras implementations, see
https://blog.keras.io/
building-autoencoders-in-keras.html
![Page 54: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/54.jpg)
Review from today's lecture
I Characterise essential di�erences between supervised,
unsupervised, semi-supervised learning approaches
I Discuss several unsupervised learning methods
I Compare and evaluate di�erent clustering methods
I Compare and evaluate di�erent distance measures
![Page 55: Applied Machine Learning Lecture 10: Unsupervised learningrichajo/dit866/lectures/l10/l10.pdf · 2020-02-25 · Anomaly detection - choosing features I Plot histogram of data, see](https://reader033.vdocuments.site/reader033/viewer/2022050217/5f631452cb6df354a15ddf33/html5/thumbnails/55.jpg)
Next two lectures
I 28 Feb: Ethics in Machine LearningI Will be given by Vilhelm Verendel
(https://www.chalmers.se/en/sta�/Pages/vilhelm-gustav-verendel.aspx)
I 3 March: Dealing with time series data