Code implementing the experiments described in the paper "On The Power of Curriculum Learning in Training Deep Networks" by Hacohen & Weinshall (ICML 2019)
Hey! I've been reading your paper and code, and I have some doubts I'd like to share with you.
I'm particularly interested in your analysis of gradients and loss surface impact of CL.
I wanted to see how you compute those gradients in your code, but I didn't find it in your repo. I have no experience in working explicitly with gradients in Keras, so this piece of code would be of huge help for me.
Hey! I've been reading your paper and code, and I have some doubts I'd like to share with you.
I'm particularly interested in your analysis of gradients and loss surface impact of CL.
I wanted to see how you compute those gradients in your code, but I didn't find it in your repo. I have no experience in working explicitly with gradients in Keras, so this piece of code would be of huge help for me.
Thanks in advance, and thank you for your time