Proposed in 2014, the interesting Generative Adversarial Network (GAN) has now many variants. You might not surprised that the relevant papers are more like statistics research. When a model was proposed, the evaluations would be based on some fundamental probability distributions, where generalized applications start. Continue reading “Deep Learning 13: Understanding Generative Adversarial Network”

# Category: Algorithm

# Two sample problem(2): kernel function, feature space and reproducing kernel map

Find Two sample problem (1) here.

We will take a look at RHKS (Reproducing Hilbert Kernel Space ) in this post. You might think of it a very statistical term but it is amazing because of various applications. You will need to refresh your mind for some linear algebra computations. We start with some basic terms and definitions. Continue reading “Two sample problem(2): kernel function, feature space and reproducing kernel map”

# Understanding SVM(2)

A brief Introduction here. (Wrote a blog about it last year, but do not think it is detailed.)

This blog is learning notes from this video (English slides but Chinese speaker). First a quick introduction on SVM, then the magic of how to solve max/min values. Also, you could find Kernel SVM. Continue reading “Understanding SVM(2)”

# Two sample problem(1): Parzen Windows, Maximum Mean Discrepancy

There is a nice tutorial from Alex. I expanded the math part to show you more details. I used latex then posted screenshots. Continue reading “Two sample problem(1): Parzen Windows, Maximum Mean Discrepancy”

# NLP 05: From Word2vec to Doc2vec: a simple example with Gensim

#### Introduction

First introduced by Mikolov 1 in 2013, the word2vec is to learn distributed representations (word embeddings) when applying neural network. It is based on the distributed hypothesis that words occur in similar contexts (neighboring words) tend to have similar meanings. Two models here: cbow ( continuous bag of words) where we use a bag of words to predict a target word and skip-gram where we use one word to predict its neighbors. For more, although not highly recommended, have a look at TensorFlow tutorial here. Continue reading “NLP 05: From Word2vec to Doc2vec: a simple example with Gensim”

# NLP 04: Log-Linear Models for Tagging Task (Python)

We will focus on POS tagging in this blog.

##### Notations

While HMM gives us a joint probability on tags and words: . Tags t and words w are one-to-one mapping, so in the series, they share the same length.

Continue reading “NLP 04: Log-Linear Models for Tagging Task (Python)”

# TensorFlow 04 : Implement a LeNet-5-like NN to classify notMNIST Images

The blog is a solution of Udacity DL Assignment 4, using a CNN to classify notMNIST images. Visit here to get a full version of my codes.

Continue reading “TensorFlow 04 : Implement a LeNet-5-like NN to classify notMNIST Images”