Machine Learning and Molecules (MLmol)
Course content
Students write their own neural network code from scratch using Python and use it to predict chemical properties of molecules. The performance is compared to standard machine learning packages such as scikit-learn, Keras, and DeepChem.
Knowledge:
- Basic principles behind Python programming, machine learning, and cheminformatics.
- Classification and regression using neural networks.
- Activation functions, back propagation using gradient descent, Overfitting, regularisation, hyperparameter optimisation, and training/validation/test sets.
- SMILES strings, molecular fingerprints, and graph convolution as applied to molecules.
Skills:
- Data manipulation and visualisation using Pandas, numpy, and Matplotlib/Seaborn.
- Manipulation of chemical data using RDKit.
- Use of scikit-learn, Keras, and graph-convolution NNs.
Competences:
- Prediction of chemical properties using machine learning.
- Critical evaluation of machine learning models.
Videolectures and classroom discussion
See Absalon
First year organic chemistry and mathematics
- ECTS
- 7,5 ECTS
- Type of assessment
-
Continuous assessment, 3 assignmentsOral exam on basis of previous submission, 30 minutes (no preparation time)
- Type of assessment details
- 3 assignments, each accounting for 8% of the final grade.
Any late assignments will receive the grade -3 and no feedback.
The oral examination account for 76% of the final grade. Submission of the project report is a prerequisite to partake in the oral exam. The exam project is scheduled for block week 7 and 8, and is due at the end of week 8.
The 30-minute individual oral examination is without preparation and based on the exam project report. The exam begins with a 5-minute presentation from the examinee, after which the internal assessors ask questions about the exam project and other course content.
The three assignments combined and the oral exam must each receive a passing grade to pass the course. - Aid
- All aids allowed
- Marking scale
- 7-point grading scale
- Censorship form
- No external censorship
Several internal examiners
- Re-exam
-
Same as the ordinary exam.
Previously passed parts of the examination do not need to be retaken.
If the student has not passed the assignments, possibly revised assignments must be submitted in the week before the oral re-examination.
If the student has not passed the oral examination, a possibly revised project report must be submitted in the week before the oral re-examination.
Criteria for exam assessment
See Learning Outcome
- Category
- Hours
- Class Instruction
- 12
- Preparation
- 93,5
- E-Learning
- 50
- Project work
- 50
- Exam
- 0,5
- English
- 206,0
Kursusinformation
- Language
- English
- Course number
- NKEB26002U
- ECTS
- 7,5 ECTS
- Programme level
- Bachelor
- Duration
-
1 block
- Placement
- Block 2, Block 3 And Block 4
- Schedulegroup
-
Much of the instruction comes from video lectures supplemented by one weekly meeting Fridays 13:15-15:00 for Q&A.
- Capacity
- No limitation – unless you register in the late-registration period (BSc and MSc) or as a credit or single subject student.
- Studyboard
- Study Board of Physics, Chemistry and Nanoscience
Contracting department
- Department of Chemistry
Contracting faculty
- Faculty of Science
Course Coordinator
- Jan Halborg Jensen (8-7371736e777c6e77496c716e7637747e376d74)
Er du BA- eller KA-studerende?
Kursusinformation for indskrevne studerende