Explore >> Select a destination
|
You are here 
|
nlml.github.io | ||
| | | | |
dennybritz.com
|
|
| | | | | All the code is also available as an Jupyter notebook on Github. | |
| | | | |
www.oranlooney.com
|
|
| | | | | In the previous article in this series we distinguished between two kinds of unsupervised learning (cluster analysis and dimensionality reduction) and discussed the former in some detail. In this installment we turn our attention to the later. In dimensionality reduction we seek a function \(f : \mathbb{R}^n \mapsto \mathbb{R}^m\) where \(n\) is the dimension of the original data \(\mathbf{X}\) and \(m\) is less than or equal to \(n\). That is, we want to map some high dimensional space into some lower dimensional space. | |
| | | | |
fa.bianp.net
|
|
| | | | | The Langevin algorithm is a simple and powerful method to sample from a probability distribution. It's a key ingredient of some machine learning methods such as diffusion models and differentially private learning. In this post, I'll derive a simple convergence analysis of this method in the special case when the ... | |
| | | | |
math.andrej.com
|
|
| | | [AI summary] The discussion revolves around the philosophical and methodological pluralism in mathematics, emphasizing that mathematics is a human-made construct with historical developments rather than an absolute, universal truth. Key points include the idea that different mathematical frameworks (e.g., classical vs. intuitionistic logic, paraconsistent logic) represent distinct 'worlds' of mathematics, each with its own standards and validity. The conversation highlights the importance of acknowledging these pluralistic perspectives without assuming a single, unifying foundation. It also touches on the role of context, the evolution of mathematical concepts, and the implications of relativism for the future of mathematics. The discussion underscores that ... | ||
