Erinevus lehekülje "Machine learning ITI8565" redaktsioonide vahel

Allikas: Kursused
Mine navigeerimisribale Mine otsikasti
 
(ei näidata sama kasutaja 70 vahepealset redaktsiooni)
1. rida: 1. rida:
 
[[Machine learning ITI8565]]
 
[[Machine learning ITI8565]]
  
Spring term 2021
+
Spring term 2025
  
 
ITI8565: Machine learning
 
ITI8565: Machine learning
  
Taught by: Sven Nõmm
+
Taught by: Prof. Sven Nõmm
 +
 
 +
Teaching assistants Mr. Jaak Kapten and Mr. Mihhail Daniljuk
  
 
EAP: 6.0
 
EAP: 6.0
  
NB! At least in the beginning of the spring term all teaching will be conducted online.  
+
Lectures on Tuesdays 12:15-13:45  U06a-209
Please joint MS Teams! Team name Machine learning ITI8565; Spring term 2021  The code to join the team is '''gkq6q3q'''
+
 
It is recommended to download and install MS Teams as standalone application and login there with TalTech UniID account.   
+
Practices on Thursdays 14:00-15:30  ICT-402
 +
 
 +
Consultations is by appointment only!  Please do not hesitate to ask for consultation!  
 +
 
 +
Please refer to TalTech Moodle page of the course and MS Teams team of the course for up to date slides and files necessary for practice sessions. 
 +
This page will be populated during the term with lecture with the lecture slides.  
 +
 
 +
 
 +
=Lectures and tentative time line =
 +
== 04.02.25 Introduction and desistance function ==
 +
 
 +
[[Media:lecture_01_intorduction_and_distance_function_ml_2025_web_version.pdf ‎|Slides]]
 +
 
 +
== 11.02.25 Cluster Analysis I ==
 +
 
 +
[[Media:lecture_02_cluster_analysis_1_ml_2025.pdf ‎|Slides]]
 +
 
 +
== 18.02.25 Cluster analysis II ==
 +
 
 +
[[Media:lecture_03_1_cluster_analysis_2_probabilistic_approach_ml_2025.pdf ‎|Slides]]
 +
 
 +
[[Media:lecture_03_2_anomaly_and_otlier_analysis_ml_2025.pdf ‎|Slides]]
 +
 
 +
== 25.02.25 Classification I ==
 +
 
 +
[[Media:lecture_04_classification_1_ml_2025.pdf ‎|Slides]]
 +
 
 +
== 04.03.25 Regression analysis == 
 +
<span style="color:red"> Deadline to submit first home assignment </span>
 +
 
 +
[[Media:lecture_05_supervised_learning_2_ml_2025.pdf ‎|Slides]]
 +
 
 +
[[Media:lecture_05_Gradient_descent_andmore_ml_2025.pdf ‎|Slides]]
 +
 
 +
== 11.03.25 Separability, Support Vector Machines, Kernel Trick ==
 +
 
 +
[[Media:lecture_06_Support_Vector_Machines_Kernel_Trick_ML_2025.pdf ‎|Slides]]
 +
 
 +
== 18.03.25 Model quality boosting ==
 +
 
 +
[[Media:lecture_07_Model_Quality_Boosting_ML_2025.pdf ‎|Slides]]
 +
 
 +
== 25.03.25 <span style="color:red"> Closed Book Test I </span> ==
  
 +
== 01.04.25 Neural networks ==
  
Lectures on Tuesdays 14:00 - 15:30  Online in MS Teams
+
== 08.04.25 Convolutional Neural Networks ==
  
Practices on Thursdays 17:45 - 19:15 Online in MS Teams
+
== 15.04.25 Sequential data modelling ==
  
 +
== 22.04.25 Deep Learning Transformers ==
  
=Lectures =
+
== 29.04.25 Generative AI ==
  
== Lecture 1  Distance function ==
+
== 06.05.25 Explainable AI ==
[[Media:Lecture_1_Intorduction_and_DistanceFunction_ML_2021.pdf ‎|Slides]]
 
  
 +
== 13.05.25 <span style="color:red"> Closed Book Test II </span> ==
  
 +
== 20.05.25 TBA ==
  
 +
Grading scale
 
*91 < score      -- grade 5 (excellent)
 
*91 < score      -- grade 5 (excellent)
 
*81 < score < 90 -- grade 4 (very good)
 
*81 < score < 90 -- grade 4 (very good)

Viimane redaktsioon: 31. jaanuar 2025, kell 12:58

Machine learning ITI8565

Spring term 2025

ITI8565: Machine learning

Taught by: Prof. Sven Nõmm

Teaching assistants Mr. Jaak Kapten and Mr. Mihhail Daniljuk

EAP: 6.0

Lectures on Tuesdays 12:15-13:45 U06a-209

Practices on Thursdays 14:00-15:30 ICT-402

Consultations is by appointment only! Please do not hesitate to ask for consultation!

Please refer to TalTech Moodle page of the course and MS Teams team of the course for up to date slides and files necessary for practice sessions. This page will be populated during the term with lecture with the lecture slides.


Lectures and tentative time line

04.02.25 Introduction and desistance function

Slides

11.02.25 Cluster Analysis I

Slides

18.02.25 Cluster analysis II

Slides

Slides

25.02.25 Classification I

Slides

04.03.25 Regression analysis

Deadline to submit first home assignment

Slides

Slides

11.03.25 Separability, Support Vector Machines, Kernel Trick

Slides

18.03.25 Model quality boosting

Slides

25.03.25 Closed Book Test I

01.04.25 Neural networks

08.04.25 Convolutional Neural Networks

15.04.25 Sequential data modelling

22.04.25 Deep Learning Transformers

29.04.25 Generative AI

06.05.25 Explainable AI

13.05.25 Closed Book Test II

20.05.25 TBA

Grading scale

  • 91 < score -- grade 5 (excellent)
  • 81 < score < 90 -- grade 4 (very good)
  • 71 < score < 80 -- grade 3 (good)
  • 61 < score < 70 -- grade 2 (satisfactory)
  • 51 < score < 60 -- grade 1 (acceptable)

score ≤ 50 -- a student has failed the course