Skip to main content
1 vote

Does 1-bit quantization (layers with boolean tensors) machine learning exist?

1-bit quantization does exist, at least at the inference stage: a common approach is to constrain weights (and sometimes activations) to be -1 or +1. I'd recommend this survey paper for a good ...
Alexander Wan's user avatar
1 vote

How can an MLP be implemented with convolutional layers?

When I try to understand convolutional layer, I always look at the shape of filters. I try to stack matrices in my mind and visualize the convolution. If we consider that each point has 3 features (x, ...
Mihnea Aleman's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible