Lecture - Theories of Deep Learning MT25, V, Controlling the exponential growth of variance and correlation

Created: October 29, 2025 | Updated: November 14, 2025 | Read markdown | About these notes

---

• Course - Theories of Deep Learning MT25^U

This lecture mainly covered the results in Paper - Exponential expressivity in deep neural networks through transient chaos (2016)^U.

Papers mentioned

• Understanding the difficulty of training deep feedforward neural networks
• Paper - Exponential expressivity in deep neural networks through transient chaos (2016)^U

---

Related posts

• Course - Theories of Deep Learning MT25^U

  (outgoing)
• Paper - Exponential expressivity in deep neural networks through transient chaos (2016)^U

  (outgoing)
• Paper - When and when can deep networks avoid the curse of dimensionality, Poggio (2016)^U

  (sim: 0.638)
• Lecture - Theories of Deep Learning MT25, VI, Controlling the variance of the Jacobian's spectrum^U

  (sim: 0.77)
• Lecture - Theories of Deep Learning MT25, VII, Stochastic gradient descent and its extensions^U

  (sim: 0.691)
• Lecture - Theories of Deep Learning MT25, XIII, Autoencoders^U

  (sim: 0.681)