1. LEARNING & MEMORY
Jaan Aru

2. Deep neural nets

3. Learning through weight changes

5. Feedback connections!

6. But the biggest difference?

7. The most famous patient: H.M.

8. Patient H.M.
Hippocampus
Medial temporal lobe

9. Types of memory

10. MEMENTO

11. Patient H.M. demonstrates that ...
1) medial temporal lobe is important for memory
2) but it is not necessary for all memory!
3) there is a difference between short-term and long term memory
4) there is a difference between declarative and procedural memory
5) medial temporal lobe is necessary for long term declarative memory

15. Taxonomy of long-term memory

16. complementary learning systems (CLS)
intelligent agents must possess two learning systems neocortex and hippocampus (MTL) NC gradually acquires structured knowledge HC quickly learns the specifics of individual experiences.

18. Structured Knowledge Representation System in Neocortex
hippocampus

19. Instance-Based Representation in the Hippocampal System
pattern separation: DG is crucial in selecting a distinct neural activity pattern in CA3 for each experience pattern completion : in CA3 reactivation of part of the pattern that was activated during storage can reactivate the rest of the pattern

20. Open question
What constitutes an „individual experience“? = when does hippocampus do its dance? Every moment something changes .. New experience whenever a big change in high level semantic features

22. Replay of Hippocampal Memories

24. Replay of Hippocampal Memories
Circumventing the Statistics of the Environment All the experiences don’t have the same priority! 1. Experience can have different lengths 2. replay is biased towards rewarding events Novel, significant reweighting experiences shapes neocortical learning For the cortex it is the same

25. One shot learning?

27. Can we apply it in AI?? DeepMind: ‘experience replay’
interleaved with ongoing game-play
biasing replay towards significant events
Prioritized experience replay
Its success supports the role of the hippocampus in reweighting experiences

28. external memory

29. differentiable neural computer

30. Taxonomy of long-term memory

32. ENCODING
CONSOLIDATION
RETRIEVAL

33. But what are these stored features? What gets actually stored?
ENCODING
But what are these stored features?
What gets actually stored?

37. One image, hundred ways to encode it

38. How you encode it determines how you remember

39. For remembering, try to go mentally back to the situation where you
ENCODING
CONSOLIDATION
RETRIEVAL
For remembering, try to
go mentally back to the
situation where you
learned it

40. Encoding what?
What you encode determines what you remember! What you encode depends on your mood, attention, other thoughts and associations – it is highly variable Adult humans mostly do not encode sensory features, but rather semantic concepts Transfer learning is hard with sensory features, but easy with semantic concepts

43. Transfer learning
Transfer learning is as good as your features Transfer learning is hard with sensory features, but easy with semantic features As two similar things might be very different in sensory space Whereas semantic features are multisensory / amodal – different sensory features can be combined

47. Summary
ANNs learn structured knowledge Learning single experiences is essential Based on hippocampus Prioritized replay to cortex Applying in AI has been a success (DeepMind) One image, hundred ways to encode it Semantic encoding enables transfer