This is just for me to remember the new posts I want to write about / refactor: - [ ] **Attention-based Models & self-attention** - [ ] Graph NN - [x] Dimensionality reduction approaches - [ ] Autoencoders history - [ ] GANs history - [ ] Paper: Analytic Manifold Learning: Unifying & Evaluating Representations for Continuous Control - [ ] Paper: Phasic Policy Gradient https://arxiv.org/abs/2009.04416 - [ ] What is a matrix? Matrices as data vs Matrices as transformations. + interpretations. [Inspiration](https://jeremykun.com/2016/04/18/singular-value-decomposition-part-1-perspectives-on-linear-algebra/) [Inspiration](http://gregorygundersen.com/blog/2018/10/24/matrices/) - [ ] **Particle filters vs HMM vs RL vs (Contextual) Bayesian Optimization vs Multi-Bandit Arm** - [ ] **How to evaluate models: Common metrics depending on model's nature Precision/Recall Single&Multiple Variables, ROC AUC...** - [ ] **Continual learning**: Summarize references from Raia Hadsell M2L talk: https://www.sciencedirect.com/science/article/pii/S1364661320302199 Refactor/Review: - [x] First three lectures of RL: Change order and unify style - [ ] **Distributions post: Add distributions and meaning, Add KL generalizations, Jensen–Shannon divergence, Total variation distance, Wasserstein metric...** - [ ] Model-free RL - [ ] Model-based RL: Watch new lectures and try to re-organize writing - [ ] Compress oleguer profile picture
This is just for me to remember the new posts I want to write about / refactor:
Refactor/Review: