Erinevus lehekülje "Machine learning ITI8565" redaktsioonide vahel
Mine navigeerimisribale
Mine otsikasti
| (ei näidata sama kasutaja 100 vahepealset redaktsiooni) | |||
| 1. rida: | 1. rida: | ||
[[Machine learning ITI8565]] | [[Machine learning ITI8565]] | ||
| − | Spring | + | Spring term 2024 |
ITI8565: Machine learning | ITI8565: Machine learning | ||
| 9. rida: | 9. rida: | ||
EAP: 6.0 | EAP: 6.0 | ||
| − | + | Lectures on Tuesdays 12:00-17:00 ICT-A2 | |
| − | + | ||
| − | + | Practices on Thursdays 14:00-15:30 ICT-401 | |
| + | |||
| + | Consultations is by appointment only! Please do not hesitate to ask for consultation! | ||
| − | |||
| − | |||
| − | |||
=Lectures = | =Lectures = | ||
| − | |||
| − | |||
| − | == | + | == Week 1 Introduction, Distance function == |
| − | [[Media: | + | [[Media:lecture_01_intorduction_and_distance_function_ml_2024_web_version.pdf |Slides]] |
| + | |||
| + | == Week 2 Cluster analysis I == | ||
| + | [[Media:lecture_02_cluster_analysis_1_ml_2024.pdf |Slides]] | ||
| + | |||
| + | == Week 3 Cluster analysis II (Probabilistic approach; Outlier and Anomaly Analysis) == | ||
| + | [[Media:lecture_03_1_cluster_analysis_2_probabilistic_approach_ml_2024.pdf |Slides]] | ||
| + | |||
| + | [[Media:lecture_03_2_anomaly_and_otlier_analysis_ml_2024.pdf |Slides]] | ||
| + | |||
| + | == Week 4 Supervised learning I: Classification == | ||
| + | [[Media:lecture_04_classification_1_ml_2024.pdf |Slides]] | ||
| + | |||
| + | == Week 5 Supervised learning II: Regression == | ||
| + | [[Media:lecture_05_supervised_learning_2_ml_2024.pdf |Slides]] | ||
| + | |||
| + | == Week 6 Supervised learning III: Gradient descent == | ||
| + | [[Media:lecture_06_Gradient_descent_andmore_ml_2024.pdf |Slides]] | ||
| + | |||
| + | [[Media:lecture_06_Support_Vector_Machines_Kernel_Trick_ML_2024.pdf |Slides]] | ||
| + | |||
| + | == Week 7 Supervised learning V: Model quality boosting == | ||
| + | [[Media:lecture_07_Model_Quality_Boosting_ML_2024.pdf |Slides]] | ||
| + | |||
| + | == Week 8 Closed book test 1 == | ||
| + | |||
| + | == Week 9 Neural Networks I == | ||
| + | [[Media: lecture_8_neural_networks_ML_2024.pdf |Slides part I ]] | ||
| + | [[Media: Lecture_8_part_2_neural_networks_ML_2024.pdf |Slides part II]] | ||
| + | [[Media: lecture_08_part_3_neural_networks_2_ML_2024.pdf |Slides part III]] | ||
| + | |||
| + | == Week 10 Sequential processes modelling: from Markov Models to LSTM == | ||
| + | |||
| + | |||
| + | == Week 11 Deep Learning I: Transformers== | ||
| + | TBA | ||
| + | |||
| + | == Week 12 Deep Learning II: Convolutional neural networks== | ||
| + | TBA | ||
| + | |||
| + | == Week 13 Deep Learning III: Generative AI == | ||
| + | TBA | ||
| + | |||
| + | == Week 14 Explainable AI== | ||
| + | TBA | ||
| + | |||
| + | |||
| − | |||
*91 < score -- grade 5 (excellent) | *91 < score -- grade 5 (excellent) | ||
Viimane redaktsioon: 25. märts 2024, kell 11:32
Spring term 2024
ITI8565: Machine learning
Taught by: Sven Nõmm
EAP: 6.0
Lectures on Tuesdays 12:00-17:00 ICT-A2
Practices on Thursdays 14:00-15:30 ICT-401
Consultations is by appointment only! Please do not hesitate to ask for consultation!
Lectures
Week 1 Introduction, Distance function
Week 2 Cluster analysis I
Week 3 Cluster analysis II (Probabilistic approach; Outlier and Anomaly Analysis)
Week 4 Supervised learning I: Classification
Week 5 Supervised learning II: Regression
Week 6 Supervised learning III: Gradient descent
Week 7 Supervised learning V: Model quality boosting
Week 8 Closed book test 1
Week 9 Neural Networks I
Slides part I Slides part II Slides part III
Week 10 Sequential processes modelling: from Markov Models to LSTM
Week 11 Deep Learning I: Transformers
TBA
Week 12 Deep Learning II: Convolutional neural networks
TBA
Week 13 Deep Learning III: Generative AI
TBA
Week 14 Explainable AI
TBA
- 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