UC BERKELEY COGSCI 1 MIDTERM 1
2026/2027 ACTUAL QUESTIONS WITH
VERIFIED ANSWERS.
Binary boolean functions - correct answer-domain is made up
of binary values and range is the same
And function - correct answer-(true, true) -> true - all other
combinations -> false
Or function - correct answer-(false, false) -> false - all other
combinations -> true
Xor function - correct answer-function where (false, true) or
(true , false) = true, (true,true) or (false, false) = false
Mcculloch and Pitts - correct answer-discovered neurons are
like logic gates and Turing machines → brains are computers
,Hebbian learning - correct answer-neurons that fire together
wire together - after one neuron excites another repeatedly it
becomes more efficient at exciting the neuron.
Perceptrons - correct answer-(Rosenblatt)
- System to allow correct responses to particular inputs (stimuli)
- Two layers of simple interconnected units (input, output)
- Each unit may be active or inactive
- Response that system makes depends on strengths of
connections
- Limited: Can't do XOR problem
Perceptron convergence rule - correct answer-requires
supervision of this algorithm - requires feedback about incorrect
solutions to the problem and then uses that feedback to reduce
erros.
Small delta (curly looking d) - correct answer-discrepancy
between intended and actual output
Big delta (triangle) - correct answer-the adjustment to make
after applying a rule in a neural network
,Linearly separable - correct answer-you can draw a straight line
to separate inputs that a value of 1 and those that receive a
value of 0 (AND and OR are linearly separable, XOR is not)
Single layer networks - correct answer-Mapping function: Maps
a set of items (domain) to a set of items (range).
Function: Each item in the domain has one (and only one)
value in the range.
Multilayer networks - correct answer-Units arranged in layers:
Input layer
Hidden layer(s)
Output layer
Hidden layer - correct answer-The second layer of a three-layer
network where the input layer sends its signals, performs
intermediary processing
, Feedforward - correct answer-activation spreads forward
through the network - there is no spread between units in a
layer or backwards
Backpropagation algorithm - correct answer-a learning
algorithm in multilayer neural networks in which error is spread
backwards through the network from the output units to the
hidden units, allowing the network to modify the weights of the
units in the hidden layers
Local algorithms - correct answer-individual unit's weight
changes directly as a function of the inputs to and outputs from
that unit. It's like Hebbian learning. This algorithm is more
biologically plausible than backpropagation.
Competitive networks - correct answer-each out put fires in
response to a particular set of input patterns. The unit that fires
the most will win the competition. These are good for
classification tasks.
Unsupervised learning - correct answer-like Hebbian learning -
no feedback required - it's like classical conditioning
2026/2027 ACTUAL QUESTIONS WITH
VERIFIED ANSWERS.
Binary boolean functions - correct answer-domain is made up
of binary values and range is the same
And function - correct answer-(true, true) -> true - all other
combinations -> false
Or function - correct answer-(false, false) -> false - all other
combinations -> true
Xor function - correct answer-function where (false, true) or
(true , false) = true, (true,true) or (false, false) = false
Mcculloch and Pitts - correct answer-discovered neurons are
like logic gates and Turing machines → brains are computers
,Hebbian learning - correct answer-neurons that fire together
wire together - after one neuron excites another repeatedly it
becomes more efficient at exciting the neuron.
Perceptrons - correct answer-(Rosenblatt)
- System to allow correct responses to particular inputs (stimuli)
- Two layers of simple interconnected units (input, output)
- Each unit may be active or inactive
- Response that system makes depends on strengths of
connections
- Limited: Can't do XOR problem
Perceptron convergence rule - correct answer-requires
supervision of this algorithm - requires feedback about incorrect
solutions to the problem and then uses that feedback to reduce
erros.
Small delta (curly looking d) - correct answer-discrepancy
between intended and actual output
Big delta (triangle) - correct answer-the adjustment to make
after applying a rule in a neural network
,Linearly separable - correct answer-you can draw a straight line
to separate inputs that a value of 1 and those that receive a
value of 0 (AND and OR are linearly separable, XOR is not)
Single layer networks - correct answer-Mapping function: Maps
a set of items (domain) to a set of items (range).
Function: Each item in the domain has one (and only one)
value in the range.
Multilayer networks - correct answer-Units arranged in layers:
Input layer
Hidden layer(s)
Output layer
Hidden layer - correct answer-The second layer of a three-layer
network where the input layer sends its signals, performs
intermediary processing
, Feedforward - correct answer-activation spreads forward
through the network - there is no spread between units in a
layer or backwards
Backpropagation algorithm - correct answer-a learning
algorithm in multilayer neural networks in which error is spread
backwards through the network from the output units to the
hidden units, allowing the network to modify the weights of the
units in the hidden layers
Local algorithms - correct answer-individual unit's weight
changes directly as a function of the inputs to and outputs from
that unit. It's like Hebbian learning. This algorithm is more
biologically plausible than backpropagation.
Competitive networks - correct answer-each out put fires in
response to a particular set of input patterns. The unit that fires
the most will win the competition. These are good for
classification tasks.
Unsupervised learning - correct answer-like Hebbian learning -
no feedback required - it's like classical conditioning
