Complementary Learning Systems

Question 1

What is the goal of learning?

Answer 1

Developing an internal representation of allowing one to predict what will happen next, making inferences about unseen elements of environment

Question 2

Simple Neocortical Model

Answer 2

After training, if a network is given information about some properties of an object, the network can make a guess about other properties of that thing
Sensory input (sees beak, hears tweeting, smells bird feather) → internal representation figures it is a bird

Question 3

Hebbian Learning

Answer 3

“Neurons that fire together, wire together” - works effectively using neuroscience, this helps learn that “birds can fly” but has difficulty picking up on content such as “penguins cannot fly”

Question 4

Error-driven

Answer 4

Learning by reconstruction
Allows you to contrast real world and internal presentation and tweak it accordingly. Memorizing shirt color example, looking down and realizing you missed some things, then you add some more inputs to your internal representation, more selective in the weight changes that it makes, learns from the errors made in your models

Question 5

Gradual vs One-time Learning

Answer 5

Neocortex uses gradual learning, but we also have the ability to learn rapidly (episodic memory)
If we want to learn after one trial, we need to make larger weight changes

Question 6

Catastrophic Interference

Answer 6

When you need to learn a new piece of information (that a penguin is a bird that doesn’t fly) it can lead to to an old piece of information being forgotten
Hippocampus doesn’t have this problem

Question 7

Hippocampus’s function for memory consolidation

Answer 7

Can assign distinct, minimally overlapping representations, rapidly learning individual episodes
Helps with slow extraction of statistics and correlations across episodic memories
Can sound taxing and necessary for huge capacity but most of the episodic memory isn’t retained
Begins to consolidate episodic memories into semantic memories

Question 8

Pattern Completion

Answer 8

The hippocampus can rapidly memorize patterns of cortical activity in entorhinal cortex so they can be recalled later, given a partial reminder

The cortex can do pattern completion but only after lots of exposure to information

Question 9

Pattern Seperation

Answer 9

Assigning of a distinct set of neurons to each memory, only done by hippocampus and not cortex

Question 10

How is sparse activity reinforced?

Answer 10

Inhibitory interneurons and sparse connecitvity

Question 11

Describe CA3 region

Answer 11

Through trisynpatic pathway, there is sparse activity and connectivity

Question 12

Limitation of Hebbian Learning

Answer 12

Trouble making fine distinctions, does not have any provisions for fixing these errors once they happen

Question 13

Theory of Equipotentiality

Answer 13

Memories are not stored in one area of the brain; rather, the brain operates as a whole to store memories.

Question 14

LTP:

Answer 14

A process in which synaptic transmission becomes more effective as a result of recent activity;