Intermediate Activations
Intermediate activations are the values inside the network between input and output.
They matter because they show what the network is computing before the final prediction.
For a one-hidden-layer MLP:
z1 = xW1 + b1
h = relu(z1)
scores = hW2 + b2
Here:
z1is the hidden pre-activation;his the hidden activation;scoresare the final raw outputs.
The hidden activation h is often the most useful place to inspect the model's internal representation.
Batch shape
For a batch:
X shape: (batch, input_features)
W1 shape: (input_features, hidden_units)
b1 shape: (hidden_units)
Then:
H shape: (batch, hidden_units)
The batch size stays. The feature dimension changes.
X has shape (12, 6) and W1 has shape (6, 8). What is the shape of the hidden activation matrix H?
Compute it first, then check your number.
HintBatch stays first
(12, 6) x (6, 8) gives (12, 8).
SolutionWork it out
XW1 has shape (12, 8). The bias has shape (8) and broadcasts across
the batch. ReLU keeps the shape, so H has shape (12, 8).
If a ReLU is applied to a pre-activation matrix with shape (12, 8), what is the output shape?
Compute it first, then check your number.
HintElementwise transform
ReLU changes values, not the number of entries.
SolutionWork it out
ReLU is applied element by element, so the output has the same shape:
(12, 8).