GE461 Spring 2023

User Tools

Site Tools

Trace:
start

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
start [2023/05/12 21:50]
ge461 [Week 14 (May 8, May 10)] 		start [2023/06/10 07:20] (current)
ge461 [Week 17 (May 29, May 31)]
Line 29: Line 29:
  
 ** Attendance** ** Attendance**
-  * Attendance is mandatory. A student who misses **more than 9 hours** will fail the course automatically. +  * <del>Attendance is mandatory. A student who misses **more than 9 hours** will fail the course automatically.</del> 
  
 ** Exam** ** Exam**
-  * TBD+  * The final exam will be held at EB-103 (for lastnames in the range AKSOY-GÜZEY) and EB-104 (for lastnames in the range HAMURCU-YILDIZ) during 18:00-21:00 on June 10, 2023.
  
 ** Projects** ** Projects**
Line 141: Line 141:
 Events: Feast of Ramadan holiday (Apr 21-23), National Sovereignty and Children's Day holiday (Apr 23)\\ Events: Feast of Ramadan holiday (Apr 21-23), National Sovereignty and Children's Day holiday (Apr 23)\\
  
 +{{ :ge461_supervisedlearning_part1.pdf |{{ :ge461_supervisedlearning_part2.pdf |}}}}
 ==== Week 12 (Apr 24, Apr 26) ====  ==== Week 12 (Apr 24, Apr 26) ==== 
 ** Machine learning; supervised learning; classifiers; deep learning. ** [Dündar]\\ ** Machine learning; supervised learning; classifiers; deep learning. ** [Dündar]\\
 Topic Details: Bayesian decision theory, linear discriminants, introduction to neural networks, support vector machines, decision trees.\\ Topic Details: Bayesian decision theory, linear discriminants, introduction to neural networks, support vector machines, decision trees.\\
-Slides and Additional Material: \\+Slides and Additional Material: {{ :ge461_supervisedlearning_part1.pdf |}}\\
 Project/Exercise-Problem-Set/Homework: \\ Project/Exercise-Problem-Set/Homework: \\
 References: \\ References: \\
Line 152: Line 153:
 ** Machine learning; supervised learning; classifiers; deep learning. ** [Dündar]\\ ** Machine learning; supervised learning; classifiers; deep learning. ** [Dündar]\\
 Topic Details: Bayesian decision theory, linear discriminants, introduction to neural networks, support vector machines, decision trees.\\ Topic Details: Bayesian decision theory, linear discriminants, introduction to neural networks, support vector machines, decision trees.\\
-Slides and Additional Material: \\+Slides and Additional Material: {{ :ge461_supervisedlearning_part2.pdf |}} \\
 Project/Exercise-Problem-Set/Homework: \\ Project/Exercise-Problem-Set/Homework: \\
 References: \\ References: \\
Line 168: Line 169:
 ** Machine learning in healthcare. ** [Çukur] \\ ** Machine learning in healthcare. ** [Çukur] \\
 Topic Details: Healthcare analytics: diagnostics, medical imaging, in-patient care, hospital management, risk analytics, wearables. Deep learning architectures for medical applications; \\ Topic Details: Healthcare analytics: diagnostics, medical imaging, in-patient care, hospital management, risk analytics, wearables. Deep learning architectures for medical applications; \\
-Slides and Additional Material: \\ +Slides and Additional Material: {{ :ge461_ml_in_healthcare.pdf |}}\\ 
-Project/Exercise-Problem-Set/Homework:\\+Project: {{ :ge461_pw13_description.pdf |}} {{ :ge461_pw13_data.zip |}}\\
 References: Hastie, Tibshirani and Friedman, The Elements of Statistical Learning, Ch. 11 and 14; Mead, Analog VLSI and Neural Systems, Ch. 4; Bishop, Pattern Recognition and Machine Learning, Ch. 5\\ References: Hastie, Tibshirani and Friedman, The Elements of Statistical Learning, Ch. 11 and 14; Mead, Analog VLSI and Neural Systems, Ch. 4; Bishop, Pattern Recognition and Machine Learning, Ch. 5\\
 Events: \\ Events: \\
Line 176: Line 177:
 ** Data mining; online data stream classification; applications.**  [Can] \\ ** Data mining; online data stream classification; applications.**  [Can] \\
 Topic Details: Concept drift, ensemble-based classification, text mining. \\ Topic Details: Concept drift, ensemble-based classification, text mining. \\
-Slides and Additional Material:\\ +Slides and Additional Material: {{ :GE461_dataStreamMiningSpring23.pdf |}} {{ :GE461_dataStreamHWspringVer2_2023.pdf |}}\\ 
-Project/Exercise-Problem-Set/Homework:\\+Project/Exercise-Problem-Set/Homework: {{ ge461_datastreamhwspringver1_2023_2.pdf |}}\\
 References:  \\ References:  \\
 Events: \\ Events: \\
Line 183: Line 184:
 ==== Week 17 (May 29, May 31) ====  ==== Week 17 (May 29, May 31) ==== 
 ** Reinforcement learning; applications.  ** [Tekin] \\ ** Reinforcement learning; applications.  ** [Tekin] \\
-Topic Details: Applications of Reinforcement Learning, Markov Decision Processes, Value Iteration, Q Learning\\ +Topic Details: Applications of Reinforcement Learning, Markov Decision Processes, Value Iteration, Q Learning, Multi-armed bandits \\ 
-Slides and Additional Material: \\+Slides and Additional Material: https://www.dropbox.com/s/65h9melvnvuml2x/ge461_reinforcementlearning.pdf?dl=0 \\
 Project/Exercise-Problem-Set/Homework: \\ Project/Exercise-Problem-Set/Homework: \\
 References: \\ References: \\
start.1683928219.txt.gz · Last modified: 2023/05/12 21:50 by ge461

Page Tools

Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki