MO434 - Deep Learning
Computing Institute (IC / Unicamp)Prof. Sandra Avila (sandra@ic.unicamp.br)
Important Notices:
- [06/08/2019] Classes will start on 01 / October / 2019.
Time and Place: Tuesdays and Thursdays, from 14pm to 16pm. Sala 352.
Waiters The opening hours will always be provided after classes by the teacher, or by Slack (dl-unicamp-2019.slack.com).
Data | Subject | |
---|---|---|
01/10/2019 | DL: Introduction & Course Logistics | |
03/10/2019 | [Deep] Neural Networks | |
08/10/2019 | Convolutional Neural Networks | |
10/10/2019 | CNN Architectures | |
15/10/2019 | CNN [Code] | |
17/10/2019 | Training [Deep] Neural Networks | |
24/10/2019 | Training [Deep] Neural Networks | |
29/10/2019 | Recurrent Neural Networks | |
31/10/2019 | [Object] Detection & [Semantic / Instance] Segmentation | |
05/11/2019 | Generative Adversarial Networks | |
12/11/2019 | Natural Language Processing (Prof. Roberto Lotufo) | |
21/11/2019 | Deep Learning: A Critical Appraisal | |
28/11/2019 | Understanding & Visualizing | |
05/12/2019 | Projects |
Assessment: The evaluation will be based on a practical design to be carried out in groups:
- The groups must have 3 students (the), necessarily.
- Deliveries must be made via Moodle, and the report must present an explanation of the technique implemented, illustrations of the results, and a discussion of the results obtained in the format of a scientific article, in the model suggested by the teacher.
- The project must be presented in class by the group on the scheduled date.
- The final average, M, will be calculated as: M = 0,1 x proposal + 0,2 x baseline + 0,3 x video + 0,4 x report / code
- The final concept will be assigned as follows:
- A: if M ≥ 8.5
- B: if 7.0 ≤ M <8.5
- C: if 5.0 ≤ M <7.0
- D: if M <5.0
Evaluation Delivery Dates: The dates below are subject to change.
- Proposal submission (theme & database): 10/10/2019 (10%)
- The project theme should be AI for Social Good (Education, Protecting democracy, Urban planning, Assistive technology for people with disabilities, Health, Agriculture, Environmental sustainability, Social welfare and justice, Sustainable development).
- Baseline submission: 31/10/2019 (20%)
- Presentation (videos of up to 4 minutes):
28/11/201905/12/2019 (30%). Examples 2017.2 Examples 2018.2 - Report submission & code: 05/12/2019 (40%)
Remarks:
- There will be no tests or exam for this discipline.
- Any attempted fraud in the activities of the discipline will imply a final average M = 0 (zero) for all persons involved, without prejudice to other sanctions.
References: The teacher will not follow a specific textbook, however, the following books cover most of what will be seen in class:
- "Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow", A. Géron, 2019.
- "Deep Learning", Ian Goodfellow, Yoshua Bengio, Aaron Courville, 2016.