studyofeverything

[studyofeverything]

* operator makes an iterable object be able to be used a collection of arguments of a function.

[studyofeverything]

A Boltzmann machine is a network of symmetrically connected, neuron-like units that make stochastic decisions about whether to be on or off.

Stochastic decisions

Boltzmann machines have a simple learning algorithm (Hinton & Sejnowski, 1983)

The learning algorithm is very slow in networks with many layers of feature detectors

The learning algorithm is fast in "restricted Boltzmann machines".

Restricted Boltzmann machines  have a single layer of feature detectors

Many hidden layers can be learned efficiently by composing restricted Boltzmann machines.

Boltzmann machines are used to solve two problems: search problems and learning problems.

[studyofeverything]

A module is loaded only once, regardless of the number of times it is imported. This prevents the module execution from happening over and over again if multiple imports occur.

from module import *

import all names from a module into the current namespace

The order of locating modules

The current directory

If the module isn't found, Python then searches each directory in the shell variable PYTHONPATH.

If all else fails, Python checks the default path. On UNIX, this default path is normally /usr/local/lib/python/.

If a local and a global variable have the same name, the local variable shadows the global variable.

The dir() function

dir() returns a sorted list of strings containing the names defined by a module.

dir(module)

The globals() function

The locals() function

reload() function

How to make a package

In the Phone folder

__init__.py

from Pots import Pots

from Isdn import Isdn

from G3 import G3

Pots.py

Isdn.py

G3.py

You can import the Phone module by

import Phone

Phone.Pots()

Phone.Isdn()

Phone.G3()

from Phone import *

Pots()

Isdn()

G3()

[studyofeverything]

Video Understanding Startups

Valossa, https://valossa.com/

Viisight, https://www.viisights.com/

Dextro, https://www.dextro.co/

[studyofeverything]

Autoregressive Models

An autoregressive model is a regression where that a value from a time series is regressed on previous values from that same time series.

The order of an autoregression is the number of immediately preceding values in the series that are used to predict the value at the present time.

A first-order autoregression[autoregressive model] is represented as AR(1).

The value at time t is predicted from the value at time t-1

A second-order autoregression is represented as AR(2).

The value at time t is predicted from the values at time t-1 and time t-2.

References

https://onlinecourses.science.psu.edu/stat501/node/358

[studyofeverything]

You will choose a 'specialist area' within the programme, which will determine the choice of your optional courses:

Intelligent Robotics

Agents, Knowledge and Data

Machine Learning

Natural Language Processing

You can choose from a variety of optional courses including:

Advanced Vision

Algorithmic Game Theory and Its Applications

Computer Animation and Visualisation

Machine Learning and Pattern Recognition

Natural Language Understanding

Robotics: Science and Systems

Human-Computer Interaction

Software Architecture, Process and Management

Text Technologies for Data Science

Computational Cognitive Neuroscience

[studyofeverything]

Cut and paste:

Position the cursor where you want to begin cutting.

Press v to select characters, or uppercase V to select whole lines, or Ctrl-v to select rectangular blocks (use Ctrl-q if Ctrl-v is mapped to paste).

Move the cursor to the end of what you want to cut.

Press d to cut (or y to copy).

Move to where you would like to paste.

Press P to paste before the cursor, or p to paste after.

Copy and paste is performed with the same steps except for step 4 where you would press y instead of d:

d stands for delete in Vim, which in other editors is usually called cut

y stands for yank in Vim, which in other editors is usually called copy

[studyofeverything]

“...if your hard drive is segmented into 512 byte clusters then any files smaller than 512 bytes will still take up the full 512 bytes on the disk.“

[studyofeverything]

NumPy for Matlab Users

This page gives you what are the differences between NumPy and SciPy.

Contents

Introduction

Some Key Differences

'array' or 'matrix'? Which should I use?

Short answer

Long answer

Facilities for Matrix Users

Table of Rough MATLAB-NumPy Equivalents

General Purpose Equivalents

Linear Algebra Equivalents

Notes

Customizing Your Environment

MATLAB packages/tools and equivalent for use with NumPy

Links

[studyofeverything]

“현재 미국의 노동 생산성을 100이라 할 때 일본은 78, 한국은 45라고 한다. 같은 양의 노동을 투입해도 우리나라의 최종 생산량이 미국의 절반밖에 되지 않는다는 것이다."

“미국 경제의 생산성이 높은 이유는 말단 직원들이 그다지 똑똑하지 않기 때문이기도 하다. 다시 말해 인재들을 말단 자리에 계속 남겨두지 않는다는 말이다. 미국에선 일단 능력이 확인되면 빠른 시간 내에 발탁되고 승진된다.“

“한국처럼 연공서열에 의존하거나 혈연, 지연, 학연 등 능력 이외의 요인을 중요시하는 사회에서는 인적 자원의 재배치가 훨씬 더디게 되고 결국 생산성을 떨어뜨린다.“

“우리의 생산성이 낮은 이유는 결코 인재풀(pool)이 나빠서가 아닌 것이다. 문제는 같은 인재풀을 가지고도 적재적소에 배치하지 못하는 데 있다. 적재적소에 인재를 배치한다면 경제 전체의 생산성을 충분히 더 높일 수 있다.”

[studyofeverything]

t-Distributed Stochastic Neighbor Embedding (t-SNE) is a (prize-winning) technique for dimensionality reduction that is particularly well suited for the visualization of high-dimensional datasets.

[studyofeverything]

심리학에서 구성주의(構成主義, Constructivism)는 인간이 자신의 경험으로��터 지식과 의미를 구성해낸다는 이론이다.

교육학에서는 피교육자들이 교육을 받을 때, 학습 이전의 개념을 토대로 학습이 진행된다는 의미가 된다.

[studyofeverything]

Sharing to facebook test