Given e.g. $1$M vectors of $1000$ floating points each, where every point in vectors is sampled from a uniform distribution between $-1$ to $1$, how to estimate the minimum network size required between input ($1000$ units), bottleneck (preferably $1$ unit), and output ($1000$ units) which is cable of overfitting the training data perfectly?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.