CSCI/ARTI 8950 Machine Learning

CSCI/ARTI 8950 Machine Learning

Spring 2023: Mondays 3:00pm - 3:50pm & Tuesdays and Thursdays 2:20pm - 3:35pm, Boyd GSRC Room 306

Instructor: Prof. Khaled Rasheed
Telephone: (706)542-0881
Office Hours: Thursday 4-6pm or by email appointment
Office Location: Room 518, Boyd GSRC
Email: khaled@uga.edu

Attendance Note:

I will do the lecture in person (face to face) in room 306 and all students are expected to attend unless you are sick or under quarantine. In such cases please email me and I can work with you by zoom to catch up.

Objectives:

Machine learning is a sub-field of artificial intelligence which is concerned with computer programs that can automatically improve their capabilities and/or performance by acquiring (learning) experience. The main objectives of this course are to provide students with an in-depth introduction to machine learning methods and an exploration of research problems in machine learning and its applications which may lead to work on a project or a dissertation. The course is intended primarily for computer science and artificial intelligence graduate students. Graduate students from other departments who have a strong interest and sufficient experience in artificial intelligence may also find the course interesting.

Recommended Background:

CSCI 4380/6380 Data Mining or CSCI/PHIL 4550/6550 Artificial Intelligence or CSCI 4560/6560 Evolutionary Computation (or permission of the instructor). Familiarity with basic computer algorithms and data structures and at least one high level programming language.

Topics to be Covered:

  • Part I: Machine learning techniques: Selected from inductive learning, decision trees, neural network approaches, evolutionary computation approaches, statistical and Bayesian learning, instance-based learning, feature selction and extraction, ensemble learning and deep learning.
  • Part II: Machine learning applications: Selected from data mining, bioinformatics, biomedical modeling, medical diagnosis, text classification, visual pattern recognition and/or other contemporary applications.

    Expected Work:

    Attendance; reading; assignments (some include programming and/or running existing programs); midterm exam; and term project and paper.

    Academic Honesty and Integrity:

    All academic work must meet the standards contained in "A Culture of Honesty." Students are responsible for informing themselves about those standards before performing any academic work. The penalties for academic dishonesty are severe and ignorance is not an acceptable defense.

    Group Study Policy:

    Group study is a powerful resource for graduate students and is therefore encouraged. During group study, you may discuss in detail any homework problems. However, you must write or type your homework on your own. Furthermore, you should never look at or copy a complete solution to a problem from another student's homework or allow another student to look at or copy a complete problem solution from your homework. Finally, you should acknowledge group study by listing the names of the students you studied with at the beginning or end of your homework. Participation in group study is optional and will not affect your grade in any way.

    Grading Policy:

  • Assignments: 20% (includes homeworks, programming or using packages)
  • Paper presentation: 10%
  • Paper reviews: 10%
  • Midterm Examination: 20%
  • Term Project: 40% (includes term paper and presentation)
    Students may work on their term projects in groups of up to four students each. The above distribution is only tentative and may change later. The instructor will announce any changes.

    Assignment Submission Policy

    Assignments must be turned in through eLC by the assigned deadline. Late assignments will loose 10% for every calendar day. Rare exceptions may be made by the instructor only under extenuating circumstances and in accordance with the university policies.

    Course Home-page

    A variety of materials will be made available on the ML Class Home-page at http://cobweb.cs.uga.edu/~khaled/MLcourse/. You are responsible for being aware of whatever information is posted there.

    Lecture Notes

    Copies of Dr. Rasheed's lecture notes will be available at the course eLC page.

    Textbook available for free on the web

  • "A Course in Machine Learning" by Hal Daumé III, (Free) http://ciml.info/

    Additional Books

  • "Machine Learning", Tom Mitchell. McGraw-Hill, 1997.
  • "Pattern Recognition and Machine Learning", Christopher Bishop, 2006.(free)
  • "Data Mining: Practical Machine Learning Tools and Techniques (4th edition)", Ian Witten , Eibe Frank, Mark Hall & Christopher Pal. Morgan Kaufmann, 2017.

    Web Resources

  • University of California at Irvine ML Repository
  • The WEKA Machine Learning Project
  • The Kaggle data science home

    Announcements:

    Papers

  • "Going Deeper with Convolutions" 2014. [Olivia][3-23] {download}
  • "Attention Is All You Need" 2017. [Pradeep][3-23] {download}
  • "Palatalization in RomanianAcoustic properties and perception" 2012. [Austin][3-23] {download}
  • "Motor Imagery EEG Signal Processing and Classification Using Machine Learning Approach" 2017. [De][3-27] {download}
  • "Depression Diagnosis and Drug Response Prediction via Recurrent Neural Networks and Transformers Utilizing EEG Signals" 2021. [Jingying][3-27] {download}
  • "Plenoxels: Radiance Fields without Neural Networks" 2021. [Ratish][3-28] {download}
  • "Text Similarity in Vector Space Models: A Comparative Study" 2019. [Harsha][3-28] {download}
  • "Comparison of Deep Learning and the Classical Machine Learning Algorithm for the Malware Detection" 2018. [Bemberkar][3-28] {download}
  • "Edge Machine Learning: Enabling Smart Internet of Things Applications" 2018. [Sushruth][3-30] {download}
  • "AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE" 2021. [Yousef][4-4] {download}
  • "AutoML: A survey of the state-of-the-art" 2021. [Drew][4-4] {download}
  • "Automated Classification of Text Sentiment" 2018. [Hannah][4-6] {download}
  • "DysLexML: Screening Tool for Dyslexia Using Machine Learning" 2019. [Alyssa][4-6] {download}
  • "ReconVAT: A Semi-Supervised Automatic Music Transcription Framework for Low-Resource Real-World Data" 2013. [David][4-6] {download}
  • "Denoising Diffusion Probabilistic Models" 2020. [Soham][4-10] {download}
  • "Determination of Flowing Grain Moisture Contents by Machine Learning Algorithms Using Free Space Measurement Data" 2022. [Arthur][4-11] {download}
  • "A Survey on Deep Transfer Learning" 2018. [Kyle][4-11] {download}
  • "Identification of human triple-negative breast cancer subtypes and preclinical models for selection of targeted therapies" 2011. [William][4-11] {download}
  • "A survey of methods and tools used for interpreting Random Forest" 2019. [Lauren][4-13] {download}
  • "MLOps - Definitions, Tools and Challenges" 2013. [Aathira][4-13] {download}
  • "Time series predicting of COVID-19 based on deep learning" 2013. [Nima][4-13] {download}
  • "Clustering cancer gene expression data: a comparative study" 2013. [Kevin][4-17] {download}
  • "Bag of Words and Local Spectral Descriptor for 3D Partial Shape Retrieval" 2011. [Daniel][4-18] {download}
  • "Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent from the Decision Boundary Perspective" 2022. [Nasid][4-18] {download}
  • "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network" 2016. [Advait][4-18] {download}
  • "Deep Residual Learning for Image Recognition" 2013. [Soumya][4-20] {download}
  • "Forecast of the higher heating value based on proximate analysis by using support vector machines and multilayer perceptron in bioenergy resources" 2022. [Ehsan][4-20] {download}
  • "DeepFace: Closing the Gap to Human-Level Performance in Face Verification" 2013. [Dongliang][4-24] {download}
  • "7 Types of Regression Techniques you should know!" 2015. [Matt][4-25] {download}
  • "Federated Multi-Armed Bandits" 2021. [Gabriela][4-25] {download
  • "Learning to learn by gradient descent by gradient descent" 2013. [Divyam][4-25] {download}
  • "Protein Secondary Structure Prediction Using Deep Convolutional Neural Fields" 2016. [?][?] {download}
  • "Web Application Attacks Detection Using Machine Learning Techniques" 2018. [?][?] {download}
  • "End to End Learning for Self-Driving Cars" 2016. [?][?] {download}
  • "Predicting Post Severity in Mental Health Forums " 2016. [?][?] {download}

    Assignments:

  • Assignment 1
  • Assignment 2
  • Assignment 3
  • Assignment 4
    The course syllabus is a general plan for the course; deviations announced to the class by the instructor may be necessary.

    Last modified: April 20, 2023.

    Khaled Rasheed (khaled@uga.edu)