We first prove that it is sufficient for $$\lambda_1 < \frac{1}{\gamma}$$, where $$\lambda_1$$ is the largest singular value of $$W_{rec}$$, for the vanishing gradient problem to occur.
We first prove that it is sufficient for $$\lambda_1 < \frac{1}{\gamma}$$, where $$\lambda_1$$ is the largest singular value of $$W_{rec}$$, for the vanishing gradient problem to occur.