2. 全部文章

(DeepLearning MOOC) Lesson 4: Deep Models for Text and Sequences

Category notes deep learning Series Part 4 of «Deep Learning udacity MOOC»

problems with text:

  1. often very rare word is important, e.g. retinopathy
  2. ambiguity: e.g. cat and kitty

→ need a lot of labeled data ⇒ not realistic.
⇒ unsupervised learning

similar words appear in similar context.
embedding: map words to small vectors

measure the closeness by cosine distance:

word2vec

initial: random vector …

(DeepLearning MOOC) Lesson 3: Convolutional Neural Networks

Category notes deep learning Series Part 3 of «Deep Learning udacity MOOC»

statistical invariance → weight sharing
e.g. image colors, translation invariance...

convnet

is NNs that share their weights across space.

convolution: slide a small patch of NN over the image to produce a new "image"

convnet forms a pyramid, each "stack of pincake" get larger depth and smaller area.

convolutional lingo …

(DeepLearning MOOC) Lesson 2: Deep Neural Networks

Category notes deep learning Series Part 2 of «Deep Learning udacity MOOC»

Linear models

matrix multiplication: fast with GPU
numerically stable
cannot cocatenate linear units → equivalent to one big matrix...

⇒ add non-linear units in between

rectified linear units (RELU)

chain rule: efficient computationally

back propagation

easy to compute the gradient as long as the function Y(X) is made of simple blocks …

在java程序里使用weka进行机器学习

Category soft ml weka java

之前一直用weka的GUI界面做机器学习的任务, 感觉这个软件虽然界面丑, 不过确实是快速开展机器学期的利器. 关于GUI的weka使用以后有时间再写. 今天这篇记录一下最近使用的java版本的weka …

[Algorithms II] Week 6-3 Intractability

Category notes algorithm Series Part 13 of «Algorithms Princeton MOOC II»

1. Introduction to Intractability

recall model of computation: DFA
a univeral model of computation: turing machine
→ no more powerful model of computation.
Turing machine can compute any function that can be computed by a physically harnessable process of the natural world.

bottom line: turing machine is a simple and universal …

[Algorithms II] Week 6-2 Linear Programming

Category notes algorithm Series Part 12 of «Algorithms Princeton MOOC II»

simplex algo: top 10 algo of the 20th century (ever?).

what is linear programming:
a general problem-solving model that works for:
shortest-path, maxflow, MST, matching, assignment, ...

1. Brewer-'s Problem

toy example: choose products to maximize profit.
...
feasible region: a convex polygon.

⇒ optimum solution appears at an extreme point.

standard form …