{"id":null,"code":"521153S","name":{"valueFi":"Syväoppiminen","valueEn":"Deep Learning","valueSv":""},"credits":5.0,"minCredits":5,"maxCredits":5,"tags":[{"code":"opinfi-teema-new_technologies","title":{"valueFi":"Uudet teknologiat","valueEn":"New technologies","valueSv":"Nya teknologier"}}],"createdAt":1790534917101,"contentList":[{"title":{"valueFi":"Osaamistavoitteet","valueEn":"Learning outcomes","valueSv":""},"content":{"valueFi":"Upon completion of the course, the student \r\n- Understands the fundamentals of deep learning, including deep convolutional neural networks (CNNs), recurrent neural networks (RNNs), attention (transformers) and generative adversarial networks (GANs);\r\n- Is able to implement, train and debug one's own neural networks in PyTorch;\r\n- Knows new frontiers in deep learning","valueEn":"Upon completion of the course, the student \r\n- Understands the fundamentals of deep learning, including deep convolutional neural networks (CNNs), recurrent neural networks (RNNs), attention (transformers) and generative adversarial networks (GANs);\r\n- Is able to implement, train and debug one's own neural networks in PyTorch;\r\n- Knows new frontiers in deep learning","valueSv":""}},{"title":{"valueFi":"Sisältö","valueEn":"Content","valueSv":""},"content":{"valueFi":"The introductory course on deep learning presents the basic concepts, theory, algorithms and models, and provides hands-on experience on implementing, training and utilizing deep neural networks. The topics covered include: linear and logistic regression, loss functions, fully-connected feed-forward neural networks, backpropagation, gradient descent, convolutional neural networks (CNNs), recurrent neural networks (RNNs), attention (including transformers and vision transformers), generative adversarial networks (GANs), variational autoencoder, diffusion models, and practical tips for training and utilizing deep neural networks. Various applications of deep learning in fundamental computer vision tasks, such as image classification, object detection and segmentation, are also presented. Finally, limitations, recent progress and new frontiers of deep learning are also discussed.","valueEn":"The introductory course on deep learning presents the basic concepts, theory, algorithms and models, and provides hands-on experience on implementing, training and utilizing deep neural networks. The topics covered include: linear and logistic regression, loss functions, fully-connected feed-forward neural networks, backpropagation, gradient descent, convolutional neural networks (CNNs), recurrent neural networks (RNNs), attention (including transformers and vision transformers), generative adversarial networks (GANs), variational autoencoder, diffusion models, and practical tips for training and utilizing deep neural networks. Various applications of deep learning in fundamental computer vision tasks, such as image classification, object detection and segmentation, are also presented. Finally, limitations, recent progress and new frontiers of deep learning are also discussed.","valueSv":""}},{"title":{"valueFi":"Suoritustavat","valueEn":"Study Methods","valueSv":""},"content":{"valueFi":"The course is completed through homework assignments and either midterm exams or a final exam.","valueEn":"The course is completed through homework assignments and either midterm exams or a final exam.","valueSv":""}},{"title":{"valueFi":"Toteutustavat","valueEn":"Teaching Methods","valueSv":""},"content":{"valueFi":"The course consists of lectures (20 h), programming assignments (40 h), and independent study (75 h). Students can attend the lectures either in person or online. Video recordings are available in Moodle. Two midterm exams are held in the classroom. Final exams are held in EXAM.","valueEn":"The course consists of lectures (20 h), programming assignments (40 h), and independent study (75 h). Students can attend the lectures either in person or online. Video recordings are available in Moodle. Two midterm exams are held in the classroom. Final exams are held in EXAM.","valueSv":""}},{"title":{"valueFi":"Oppimateriaalit","valueEn":"Learning material","valueSv":""},"content":{"valueFi":"<p>Learning material is available in Moodle.</p>","valueEn":"<p>Learning material is available in Moodle.</p>","valueSv":""}},{"title":{"valueFi":"Lisätiedot","valueEn":"Further information","valueSv":""},"content":{"valueFi":"","valueEn":"","valueSv":""}},{"title":{"valueFi":"Kurssikirjallisuus","valueEn":"Literature","valueSv":""},"content":{"valueFi":"","valueEn":"","valueSv":""}},{"title":{"valueFi":"Esitietovaatimukset","valueEn":"Qualifications","valueSv":""},"content":{"valueFi":"Basic engineering mathematics, especially knowledge of probability, statistics and linear algebra. Basic Python programming skills are highly recommended, such as 521141P Elementary programming course. Completion of the courses 521289S Machine Learning and 521467A Digital Image Processing are very beneficial but not a prerequisite.","valueEn":"Basic engineering mathematics, especially knowledge of probability, statistics and linear algebra. Basic Python programming skills are highly recommended, such as 521141P Elementary programming course. Completion of the courses 521289S Machine Learning and 521467A Digital Image Processing are very beneficial but not a prerequisite.","valueSv":""}},{"title":{"valueFi":"Arviointiasteikko","valueEn":"Assessment scale","valueSv":""},"content":{"valueFi":"1-5/HYL","valueEn":"1-5/FAIL","valueSv":"1-5/FAIL"}},{"title":{"valueFi":"Arviointikriteerit","valueEn":"Assessment criteria","valueSv":""},"content":{"valueFi":"","valueEn":"","valueSv":""}},{"title":{"valueFi":"Arviointikriteerit 2","valueEn":"Evaluation criteria 2","valueSv":""},"content":{"valueFi":"","valueEn":"","valueSv":""}},{"title":{"valueFi":"Arviointikriteerit 3","valueEn":"Evaluation criteria 3","valueSv":""},"content":{"valueFi":"","valueEn":"","valueSv":""}},{"title":{"valueFi":"Arviointikriteerit 4","valueEn":"Evaluation criteria 4","valueSv":""},"content":{"valueFi":"","valueEn":"","valueSv":""}},{"title":{"valueFi":"Pääasiallinen opetuskieli","valueEn":"Primary Teaching Language","valueSv":""},"content":{"valueFi":"englanti","valueEn":"English","valueSv":"engelska"}},{"title":{"valueFi":"Taso","valueEn":"Level","valueSv":""},"content":{"valueFi":"Syventävät opinnot","valueEn":"Advanced Studies","valueSv":"Syventävät opinnot"}},{"title":{"valueFi":"Oppiaine","valueEn":"Subject","valueSv":""},"content":{"valueFi":"Tietotekniikka","valueEn":"Computer Science and Engineering","valueSv":""}},{"title":{"valueFi":"Vastuuhenkilöt","valueEn":"Person in charge","valueSv":""},"content":{"valueFi":"Janne Mustaniemi","valueEn":"Janne Mustaniemi","valueSv":"Janne Mustaniemi"}},{"title":{"valueFi":"Luokittelu","valueEn":"Classification","valueSv":""},"content":{"valueFi":"Uudet teknologiat","valueEn":"New technologies","valueSv":"Nya teknologier"}},{"title":{"valueFi":"Linkit","valueEn":"Links","valueSv":""},"content":{"valueFi":"","valueEn":"","valueSv":""}}]}