Lecture - Theories of Deep Learning MT25, XIV, Generative adversarial networks

Created: November 18, 2025 | Updated: November 18, 2025 | About these notes

[[Course - Theories of Deep Learning MT25]]^U
Adversarial examples are transferable across nets
- Nets for the same task learn the same function, so this is not super surprising
Cool visualisations of the decision regions for deep nets
Provable defence: design the models to guarantee

[[Course - Theories of Deep Learning MT25]]^U

(outgoing)
[[Lecture - Theories of Deep Learning MT25, XII, Vulnerabilities in deep learning models]]^U

(sim: 0.642)
[[Lecture - Theories of Deep Learning MT25, XIII, Autoencoders]]^U

(sim: 0.595)
[[Lecture - Theories of Deep Learning MT25, II, Why deep learning]]^U

(sim: 0.594)
[[Lecture - Theories of Deep Learning MT25, XI, Visualising the filters and response in a CNN]]^U

(sim: 0.551)
[[Lecture - Machine Learning MT23, XIV]]^U

(sim: 0.546)