ob
  • about
  • blog
  • notes (current)
  • misc
  • explore
  • study
Home Notes University Notes Part C Courses MT25 Theories of Deep Learning Lectures Theories of Deep Learning MT25, II, Why deep learning Theories of Deep Learning MT25, III, Exponential expressivity with depth Theories of Deep Learning MT25, IV, Data classes for which DNNs can overcome the curse of dimensionality Theories of Deep Learning MT25, V, Controlling the exponential growth of variance and correlation Theories of Deep Learning MT25, VI, Controlling the variance of the Jacobian's spectrum Theories of Deep Learning MT25, VII, Stochastic gradient descent and its extensions Theories of Deep Learning MT25, VIII, Optimisation algorithms for training DNNs Theories of Deep Learning MT25, XI, Visualising the filters and response in a CNN Theories of Deep Learning MT25, XII, The scattering transform and into auto-encoders Theories of Deep Learning MT25, XIII, Autoencoders
Theories of Deep Learning MT25, XIV, Generative adversarial networks Theories of Deep Learning MT25, XV, A few things we missed and a summary Theories of Deep Learning MT25, XVI, Ingredients for a successful mini-project report

Lecture - Theories of Deep Learning MT25, XIII, Autoencoders

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


  • Course - Theories of Deep Learning MT25U



Related posts
  • Course - Theories of Deep Learning MT25U
    (outgoing)
  • Lecture - Theories of Deep Learning MT25, VII, Stochastic gradient descent and its extensionsU
    (sim: 0.7)
  • Lecture - Machine Learning MT23, XIVU
    (sim: 0.75)
  • Lecture - Machine Learning MT23, XVIU
    (sim: 0.732)
  • Lecture - Machine Learning MT23, XVIIU
    (sim: 0.725)
  • Lecture - Machine Learning MT23, XIIIU
    (sim: 0.684)
© Copyright 2026 Olly Britton. Last updated: May 19, 2026.