Cog Sci Exam Prep Test Quizzes Solved 100%
Correct| Verified Solutions-Newest 2025
Connectionist network - ✔✔Model mimicking brain's neural connections. Each unit is
not actual neurons.
Weighted connections - ✔✔Strength of links between connectionist units.
Feed-forward network - ✔✔Information flows in one direction only.
Hidden units - ✔✔Intermediate processing units in neural networks.
How are connectionist networks programed - ✔✔The number of states and
connections are set up with random values for the connections. Then data is sent
through the model and it's connections are modified using back propagation
Back propagation algorithm - ✔✔Method for training neural networks. Takes result
of running a datapoint through the model and modifies the connection strengths.
Comparisons of Connectionist networks and the human brain - ✔✔Units are not
neurons, brain is much bigger, the general function is the same
Local optimal solution - ✔✔Best solution within a limited area.
Global optimal solution - ✔✔Best overall solution across entire search space.
, How to always get a global optimal solution - ✔✔Run back propagation with many
different starting values for the weighted connections
Overfitting - ✔✔Model too closely matches training data so it cannot adjust to new
test data.
Regular verbs - ✔✔Follow standard rules for past tense formation.
Irregular verbs - ✔✔Do not follow standard past tense rules.
Three stages children go through when learning verbs - ✔✔Stage 1 - learn case by
case examples
Stage 2 - start generalizing basic rule to all verbs
Stage 3 - use verb rules correctly
Overregularization Error - ✔✔Applying a rule to all cases. This happens in stage 2 of
children learning verbs
Inspiration for PSSH - ✔✔conscious logical reasoning
Inspiration for Connectionism - ✔✔neurons in the brain
Strengths and weaknesses of PSSH - ✔✔expands preexisting knowledge, but have to
preprogram lots of rules
Strengths and weakness of connectionism - ✔✔pattern recognition, but don't really
know how it works
Correct| Verified Solutions-Newest 2025
Connectionist network - ✔✔Model mimicking brain's neural connections. Each unit is
not actual neurons.
Weighted connections - ✔✔Strength of links between connectionist units.
Feed-forward network - ✔✔Information flows in one direction only.
Hidden units - ✔✔Intermediate processing units in neural networks.
How are connectionist networks programed - ✔✔The number of states and
connections are set up with random values for the connections. Then data is sent
through the model and it's connections are modified using back propagation
Back propagation algorithm - ✔✔Method for training neural networks. Takes result
of running a datapoint through the model and modifies the connection strengths.
Comparisons of Connectionist networks and the human brain - ✔✔Units are not
neurons, brain is much bigger, the general function is the same
Local optimal solution - ✔✔Best solution within a limited area.
Global optimal solution - ✔✔Best overall solution across entire search space.
, How to always get a global optimal solution - ✔✔Run back propagation with many
different starting values for the weighted connections
Overfitting - ✔✔Model too closely matches training data so it cannot adjust to new
test data.
Regular verbs - ✔✔Follow standard rules for past tense formation.
Irregular verbs - ✔✔Do not follow standard past tense rules.
Three stages children go through when learning verbs - ✔✔Stage 1 - learn case by
case examples
Stage 2 - start generalizing basic rule to all verbs
Stage 3 - use verb rules correctly
Overregularization Error - ✔✔Applying a rule to all cases. This happens in stage 2 of
children learning verbs
Inspiration for PSSH - ✔✔conscious logical reasoning
Inspiration for Connectionism - ✔✔neurons in the brain
Strengths and weaknesses of PSSH - ✔✔expands preexisting knowledge, but have to
preprogram lots of rules
Strengths and weakness of connectionism - ✔✔pattern recognition, but don't really
know how it works
