Deep learning theory lecture notes [Telgarsky] - Printable Version +- MKLab (https://mklab.gr) +-- Forum: [INDEX] (https://mklab.gr/forumdisplay.php?fid=1) +--- Forum: ARTFICIAL INTELLIGENCE (AI) (https://mklab.gr/forumdisplay.php?fid=5) +---- Forum: BOOKS (https://mklab.gr/forumdisplay.php?fid=32) +---- Thread: Deep learning theory lecture notes [Telgarsky] (/showthread.php?tid=388)

Deep learning theory lecture notes [Telgarsky] - mklabgr - 06-15-2026 Deep learning theory lecture notes  BY Matus Telgarsky Summary [b]Philosophy of these notes. Two key ideas determined what has been included so far.[/b] I aim to provide simplified proofs over what appears in the literature, ideally reducing difficult things to something that fits in a single lecture. I have primarily focused on a classical perspective of achieving a low test error for binary classification with IID data via standard (typically ReLU) feedforward networks. [b]Organization. [/b] Following the second point above, the classical view decomposes the test error into three parts. [b]Approximation (starts in section 1): given a classification problem, there exists a deep network which achieves low error over the distribution.[/b] [b]Optimization (starts in section 6): given a finite training set for a classification problem, there exist algorithms to find predictors with low training error and low complexity.[/b] [b]Generalization (starts in section 11): the gap between training and testing error is small for low complexity networks.[/b] BOOK PAGE