Unsupervised Learning

4 posts in this tag

PCA of High Dimensional Trajectory

Motivation When you think about random walks, what shape do you think about? Is it like this? Or this? These are good examples of random walks in two or three dimensions. But what about random walks in higher dimensions?

Jan 22, 2022

Note on Modern Hopfield Network and Transformers

Motivation There is a resurgent of interest in investigating and developing Hopfield network in recent years. This development is quite exciting in that it connect classic models in physics and machine learning to modern techniques like transformers.

Nov 15, 2021

Note on Hopfield Network

Rationale Hopfield Network can be viewed an energy based model: deriving all properties from it. General RNN has many complex behaviors, but setting symmetric connections can prohibit it! No oscillation is possible in a symmetric matrix.

Nov 15, 2021

Note on Word2Vec

Motivation Word2Vec is a very famous method that I heard of since the freshman year in college (yeah it comes out in 2013). Recently, some reviewer reminds us of the similarity of the “analogy” learnt by the vector representation of words and the vector analogy of image space in GAN or VAE.

Nov 27, 2020

Unsupervised Learning

PCA of High Dimensional Trajectory

Motivation When you think about random walks, what shape do you think about? Is it like this? Or this? These are good examples of random walks in two or three dimensions. But what about random walks in higher dimensions?

Unsupervised Learning PCA Geometry high dimensional random process Linear Algebra

January 22, 2022

Note on Modern Hopfield Network and Transformers

Motivation There is a resurgent of interest in investigating and developing Hopfield network in recent years. This development is quite exciting in that it connect classic models in physics and machine learning to modern techniques like transformers.

tech note Unsupervised Learning Statistical Learning ML Representation Learning RNN Transformers

November 15, 2021

Note on Hopfield Network

Rationale Hopfield Network can be viewed an energy based model: deriving all properties from it. General RNN has many complex behaviors, but setting symmetric connections can prohibit it! No oscillation is possible in a symmetric matrix.

tech note Unsupervised Learning Statistical Learning ML RNN

November 15, 2021

Note on Word2Vec

Motivation Word2Vec is a very famous method that I heard of since the freshman year in college (yeah it comes out in 2013). Recently, some reviewer reminds us of the similarity of the “analogy” learnt by the vector representation of words and the vector analogy of image space in GAN or VAE.

tech note Unsupervised Learning Statistical Learning ML Representation Learning Language NLP

November 27, 2020

Related Tags

Zebrafish (1) Waves (1) Variational (1) Tutorial Series (1) Travel (1) Transformer (1) Thesis Defense (1) Thesis (1) Spectral Bias (1) Sleep (1)