New answers tagged linear-algebra
0
votes
Accepted
Shape of biases in Transformer's Feedforward Network
The biases are vectors, and their shape should be $b_1\in \mathbb R^{d_{ff}}$ and $b_2\in \mathbb R^{d_\text{model}}$.
To verify that let's compute the shapes of the above formula (for simplicity we ...
1
vote
How Does The Scaled Dot Product's Dimensions Work Out In Mult-Head Attention?
Say you have 3-dimensional tensors Q & K of shape (B, T, C) (for Batch, Time, and Channels).
K is transposed. 'Transposing' a 3-d tensor in this case means ...
Top 50 recent answers are included
Related Tags
linear-algebra × 35neural-networks × 7
machine-learning × 6
math × 4
deep-learning × 3
papers × 3
objective-functions × 3
optimization × 3
transformer × 3
reinforcement-learning × 2
computer-vision × 2
terminology × 2
gradient-descent × 2
pytorch × 2
convolution × 2
recommender-system × 2
principal-component-analysis × 2
calculus × 2
feedforward-neural-networks × 2
convolutional-neural-networks × 1
natural-language-processing × 1
classification × 1
tensorflow × 1
reference-request × 1
ai-design × 1