Great Explanation! Thank You very much.
Anam Qureshi

Just saw this. Im not too sure if anything would change? As long as the neural net is still end to end differentiable ie. uses a continuous activation function It would be fine. Im not sure what effect binary weights might have – i’m guessing less complexity but also maybe promotion of sparsity… but again, dunno.

Show your support

Clapping shows how much you appreciated Rohan Kapur’s story.