/explore

Click through on any links that interest you or select the planets on the right to continue exploring the Outer Web.
You are here

 elonlit.com
A Theory of Deep Learning | Elements of a Vector Space
| | hackmd.io
DeepNN Notes on Why Deep Networks Generalize - HackMD
4.3 parsecs away

Travel
| |
| | jhui.github.io
"Deep learning - Computation & optimization."
3.0 parsecs away

Travel
| | [AI summary] The provided text discusses various mathematical and computational concepts relevant to deep learning, including poor conditioning in matrices, underflow/overflow in softmax functions, Jacobian and Hessian matrices, learning rate optimization using Taylor series, Newton's method, saddle points, constrained optimization with Lagrange multipliers, and KKT conditions. These concepts are crucial for understanding numerical stability, optimization algorithms, and solving constrained problems in machine learning.
| | windowsontheory.org
A blitz through classical statistical learning theory - Windows On Theory
3.9 parsecs away

Travel
| | Previous post: ML theory with bad drawings Next post: What do neural networks learn and when do they learn it, see also all seminar posts and course webpage. Lecture video (starts in slide 2 since I hit record button 30 seconds too late - sorry!) - slides (pdf) - slides (Powerpoint with ink and animation)...
| | andrea.corbellini.name
Elliptic Curve Cryptography: finite fields and discrete logarithms - Andrea Corbellini
20.3 parsecs away

Travel
| [AI summary] A technical blog post explaining elliptic curves over finite fields, covering modular arithmetic, point addition algorithms, cyclic subgroups, and the discrete logarithm problem in the context of cryptography.