Seminar Computational Intelligence A (708.111)

WS 2017/2018

Institut für Grundlagen der Informationsverarbeitung (708)


Assoc. Prof. Dr. Robert Legenstein

Office hours: by appointment (via e-mail)


Location: IGI-seminar room, Inffeldgasse 16b/I, 8010 Graz
Date: starting on Tuesday, Oct 3 2017, 15:15 - 17.00 p.m. (TUGonline)

Content of the seminar: Learning to Learn

"To illustrate the utility of learning to learn, it is worthwhile to compare machine learning to human learning. Humans encounter a continual stream of learning tasks. They do not just learn concepts of motor skills, they also learn bias, i.e., they learn how to generalize. As a result, humans are often able to generalize correctly from extremely few examples - often just a single example suffices to teach us a new thing. " [Thrun, S., & Pratt, L. (Eds.). Learning to learn. (2012)].

In this seminar, we will discuss novel work on "learning to learn". This area of machine learning deals with the following question: How can one train algorithms such that they acquire the ability to learn?

The seminar continues the discussion of last year's CI Seminar B, but is designed as a stand alone course, i.e., students are not expected to have visited the previous seminar. However, basic knowledge in neural networks is expected (e.g., the computational inteligence lecture) and basic knowledge in reinforcement lerning would be beneficial.

How to prepare and hold your talk:

The guide presented in the seminar: How to prepare and hold your talk



  1. Lake, B. M., Ullman, T. D., Tenenbaum, J. B., & Gershman, S. J. (2016). Building Machines that learn and think like people. PDF
    Only parts of it should be discussed, e.g. parts of Sections 3 and 4. It has in Section 4 also an introduction to learning to learn.

  2. Preliminaries

  3. Greff, K., Srivastava, R. K., Koutník, J., Steunebrink, B. R., & Schmidhuber, J. (2016). LSTM: A search space odyssey. IEEE transactions on neural networks and learning systems. PDF.
    The goal of this talk is to introduce LSTMs and its variants. Skip parts of the evaluations if necessary.

  4. Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning, 8(3-4), 229-256. PDF
    In this talk, the REINFORCE algorithm should be introduced after a very basic introduction into reinforcement learning

  5. Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T. P., Harley, T., ... & Kavukcuoglu, K. (2016, February). Asynchronous methods for deep reinforcement learning. In International Conference on Machine Learning.
    Describes the Asynchronous Advantage Actor Critic algorithm used in some papers below.

  6. Network-architecture search

  7. Zoph, B., & Le, Q. V. (2016). Neural architecture search with reinforcement learning. arXiv preprint arXiv:1611.01578. PDF
    Describes how network arcitectures can be learned with reinforcement learning.

  8. Learning to Learn for Reinforcement Learning

  9. Wang, J. X., Kurth-Nelson, Z., Tirumala, D., Soyer, H., Leibo, J. Z., Munos, R., ... & Botvinick, M. (2016). Learning to reinforcement learn. PDF

  10. Duan, Y., Schulman, J., Chen, X., Bartlett, P. L., Sutskever, I., & Abbeel, P. (2016). RL $^ 2$: Fast Reinforcement Learning via Slow Reinforcement Learning.  PDF.
    Possible additional topic: TRPO Trust Region Policy Optimization [3], since it is used here (but quite technical).

  11. Braun, D. A., Aertsen, A., Wolpert, D. M., & Mehring, C. (2009). Motor task variation induces structural learning. Current Biology, 19(4), 352-357. PDF
    Presents results of a behavioral experiment which studied learning-to-learn in human motor control. This is modeled in (Weinstein et al., 2017) below.

  12. Weinstein, A., & Botvinick, M. M. (2017). Structure Learning in Motor Control: A Deep Reinforcement Learning Model. arXiv preprint arXiv:1706.06827. PDF
    Models the results of Braun et al. (2009) above using model-based reinforcement learning.

  13. Learning learning rules

  14. Andrychowicz, M., Denil, M., Gomez, S., Hoffman, M. W., Pfau, D., Schaul, T., & de Freitas, N. (2016). Learning to learn by gradient descent by gradient descent.  In Advances in Neural Information Processing Systems (pp. 3981-3989).
    Uses a recurrent neural network to propose parameter update of another neural network.

  15. Li, K., & Malik, J. (2016). Learning to optimize. arXiv preprint arXiv:1606.01885. PDF
    Describes learning of an optimization algorithm

  16. Learning to learn from few examples

  17. Li, Z., Zhou, F., Chen, F., & Li, H. (2017). Meta-SGD: Learning to Learn Quickly for Few Shot Learning. arXiv preprint arXiv:1707.09835. PDF
    Shows how a stochastic gradient descent (SGD) learner can be learned for few-shot learning

  18. Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D., & Lillicrap, T. (2016). One-shot learning with memory-augmented neural networks. arXiv preprint arXiv:1605.06065. PDF

  19. Ravi, S., & Larochelle, H. (2016). Optimization as a model for few-shot learning. PDF

  20. Vinyals, O., Bengio, S., & Kudlur, M. (2015). Order matters: Sequence to sequence for sets. arXiv preprint arXiv:1511.06391. PDF
    Preliminary for the following paper

  21. Vinyals, O., Blundell, C., Lillicrap, T., & Wierstra, D. (2016). Matching networks for one shot learning. In Advances in Neural Information Processing Systems (pp. 3630-3638). PDF

Talks should be not longer than 35 minutes, and be clear, interesting and informative, rather than a reprint of the material. Select what parts of the material you want to present, and what not, and then present the selected material well (including definitions not given in the material: look them up on the web or if that is not successful, ask the seminar organizers). Often diagrams or figures are useful for a talk. on the other hand, giving in the talk numbers of references that are listed at the end is a no-no (a talk is an online process, not meant to be read). For the same reasons you can also quickly repeat earlier definitions or so if you suspect that the audience may not remember it.

Talks will be assigned at the first seminar meeting on October 3, 15:15-17:00.  Students are requested to have a quick glance at the papers prior to this meeting in order to determine their preferences. Note that the number of participants for this seminar will be limited. Preference will be given to students who

  1. are / will write a Master's Thesis at the institute
  2. are / will perform a Student's Project at the institute
  3. have registered early.

General rules:

Participation in the seminar meetings is obligatory. We also request your courtesy and attention for the seminar speaker: no smartphones, laptops, etc during a talk. Furthermore your active attention, questions, and discussion contributions are expected.

After your talk (and possibly some corrections) send pdf of your talk to Charlotte Rumpf, who will post it on the seminar webpage.


Date # Topic / paper title Presenter 1 Presenter 2 Presentation
21.11.2017 1 Building Machines that learn and think like people Gabler Jente PDF
21.11.2017 2 LSTM: A search space odyssey Gigerl Petschenig PDF
28.11.2017 3 REINFORCE + Reinforcement learning Zincke Walch PDF
5.11.2017 4 Asynchronous methods for deep reinforcement learning Loidl Nistelberger PDF
5.12.2017 5 Neural architecture search with reinforcement learning Hasler Hopfgartner PDF
12.12.2017 6 Learning to reinforcement learn Unterholzner Miguel Yuste Fernandez Alonso PDF
12.12.2017 7 RL2: Fast Reinforcement Learning via Slow Reinforcement Learning Ahmetovic Music PDF
9.1.2018 - The IGI-L2L software framework Kraisnikovic Plank PDF
9.1.2018 11 Learning to optimize Moling Reisinger canceled
16.1.2018 12 Meta-SGD: Learning to Learn Quickly for Few Shot Learning Poier Basirat PDF
16.1.2018 13 One-shot learning with memory-augmented neural networks Malle Scherr PDF
23.1.2018 8 Motor task variation induces structural learning Giegold Weichselbaum PDF