Opetussuunnitelmat
Description
| KM00DT88 | Machine Learning (5 cr) |
| Prerequisites | Not applicable |
| Objectives | The student understands the basic principles of machine learning and the difference between algorithms, traditional modelling, and deep learning. The student knows the requirements of data and observations when applying machine learning methods. The student understands the mathematics of machine learning and how to apply that by programming. The student knows how to build machine learning tools using novel methods and can understand the basic principles of models in general. The student can implement machine learning models to final state for end user and understands the requirements in terms of user’s environment, data, and documentation. |
| Content | -The basic paradigm of machine learning, modelling various phenomenon based on observations, parameter fitting and hyper parameter selection. -Data in machine learning, various data types, like numerical and categorical data. -Data processing and preparations, handling missing data. -Mathematical formalism: tensor, gradient, loss function, and their practical implementation in terms of programming. -Theory of machine learning models, selected features of Tensorflow. -History of machine learning, how to manage machine learning projects. |
| Recommended optional programme components | If necessary, the student advisor will recommend optional programme components for each student based on their individual study plan. |
| Accomplishment methods | Not applicable |
| Execution methods | Not applicable |
| Materials | Not applicable |
| Literature | Not applicable |
| Evaluation Criteria | Not applicable |
| Evaluation Criteria |
satisfactory (1-2) I know the basic concepts of artificial intelligence, the history of the field, and I can also assess on a general level where machine learning can be applied in my field now and in the future. I understand the basics of mathematics related to teaching neural networks. I can create a neural network model based on examples and teach it using data. I can use common machine learning data sources or neural network model repositories to my advantage. good (3-4) I know well the characteristics of matrix calculations related to teaching neural networks. I understand the importance of the gradient in the teaching of neural networks and I can also do the calculations related to calculating the gradient myself. I can view and modify the weight matrixes of neural network models manually. I can apply the basic concepts of machine learning in teaching neural network models. I can divide materials used in machine learning into teaching, validation and test data sets in an appropriate way and I understand the deeper meaning of these. I understand the principles of teaching algorithms. Through the exercises during the course, I have experience with different machine learning situations and related problems, and I know how to act in challenging machine learning situations. I can use the software libraries needed for machine learning. I also have the independent ability to create and teach neural network models independent of external data sources. I can search for and use data sources for machine learning as well as the latest advanced neural network implementations and further work on them based on examples. excellent (5) I fluently manage the software libraries needed in machine learning and their use. I can fluently apply data processing methods related to mathematical calculations related to machine learning. I can effortlessly process large and multidimensional data volumes for machine learning tasks. I am able to independently manage the machine learning process from start to finish, and I also show the ability for strategic thinking in machine learning tasks. I demonstrate the ability to achieve excellent results in a special challenge task related to the course. |
| Assessment Frameworks | Not applicable |
| Further Information | Not applicable |
| Responsible persons | Not applicable |
| Links | Not applicable |
Implementations
Show old implementations
- 11.03.2024 - 03.05.2024 (KM00DT88-3002 | VAI23S24K, DPM24KYTEKN, EXN24KDAPMHNU, DPD23SYTIK, DPD23SYTEKN, EXN23S24KDDMDAPMHNU, DPM24KYTIK)
19.5.2024 18:49:10