Computer science algorithm.

Enéas Silva
Mind Map by Enéas Silva, updated more than 1 year ago
Enéas Silva
Created by Enéas Silva over 3 years ago
25
0

Description

This mind map i will go over the algorithm kinds and types.

Resource summary

Computer science algorithm.
  1. Machine learn
    1. why Used
      1. Decisions about data
        1. Learn
          1. From data
        2. Scientists Says:
          1. Set of techniques
            1. Inside
              1. Even more ambitious goal
                1. Artificial inteligence
          2. What they do conceptualy
            1. Clasification
              1. Clasify some thing
                1. Analyzing
                  1. Data
                2. Algorithm name
                  1. Clasifier
                    1. Features
                      1. Values that usefully
                        1. Characterize
                          1. Things
                            1. we whish to clasify
                        2. Example
                          1. Moth Clasifier
                            1. 2 -Features
                              1. Wingspan
                                1. Mass
                                2. Training Data
                                  1. Entomologist
                                    1. Colect Data to process
                                      1. Luna
                                        1. Emperor moths
                                          1. Labeled Data

                                            Annotations:

                                            • LAbel data is a Tabel which and especialisty classify the kind of subject he is searching giving them some classification acordingly with its features. Whic is some values sizes or references to comparation.
                                  2. Represent lines in graphs
                                    1. X
                                      1. WingSpan
                                        1. Space
                                        2. Y
                                          1. Mass
                                            1. Time
                                          2. used to
                                            1. plot Data
                                              1. overlap
                                                1. Meaning
                                                  1. To have something in comon
                                                    1. TO ocupy the same area in part
                                                    2. Machine Learn Algorithm
                                                      1. Find Optimal
                                                        1. Seplaratkon
                                                          1. Clasification
                                                            1. Condition
                                                              1. X-axis
                                                                1. X(Wing Span) < 45 mm
                                                                  1. Emperor Moth
                                                                2. Y-axis
                                                                  1. Y(mass) < .75
                                                                    1. Emperor Moth

                                                                      Annotations:

                                                                      • So It takes both features to consideration and clasify within the group which one is an emperor moth and which one is the emperor moth
                                                    3. Training Data
                                                      1. Some especialist
                                                        1. Colect & Organize
                                                          1. Data
                                                  2. BAsicaly compare
                                                    1. Images
                                                      1. Sound
                                                        1. Touch
                                                        2. Decision Tree
                                                            1. Algorithm forests
                                                              1. Contains alot tree algorithm
                                                            2. Support vector machine
                                                              1. Dry lines in the graph
                                                                1. Polynomials
                                                                  1. other fancy math mathematical function
                                                                    1. To find the most accurate decision baundaries
                                                                    2. 3 lines 3D decision baundaries
                                                                2. algorithm
                                                                  1. Job
                                                                    1. at a high level
                                                                      1. Maximize
                                                                        1. Correct classification

                                                                          Annotations:

                                                                          • The algorith compare the data given to it. And try to organize in the most efective way the subejcts and informations given o it.
                                                                        2. Minimize errors
                                                                    2. Artificial Neural Network
                                                                      1. Neurons
                                                                        1. Cells
                                                                          1. Process
                                                                            1. one or more impulses
                                                                              1. from other cells
                                                                            2. Transmit
                                                                              1. Messsges
                                                                                1. using
                                                                                  1. Signals
                                                                                    1. Electrical
                                                                                      1. chemical
                                                                                  2. Their own signal to other cells
                                                                              2. Artificial Neurons
                                                                                1. Take a series of inputs
                                                                                  1. Combine them
                                                                                    1. Emits a signal

                                                                                      Annotations:

                                                                                      • Rather than beig electrical or chemical signals, artificial neurons take numbers in and spit numbers out.
                                                                                  2. Takes data entry
                                                                                    1. Process
                                                                                      1. artifical neral network
                                                                                        1. organize and analyze features
                                                                                          1. Spit out the information
                                                                                    2. First Layer
                                                                                      1. Imput Layer
                                                                                        1. Data needing classification
                                                                                          1. X-axis
                                                                                            1. Wing Span
                                                                                              1. Space
                                                                                              2. Y-axis
                                                                                                1. Mass
                                                                                                  1. Time
                                                                                            2. Last layer
                                                                                              1. Output layer
                                                                                                1. Emperor Moth
                                                                                                  1. Luna Moth
                                                                                                    1. Activation Function or transfer function
                                                                                                      1. Perform a final mathematical modifications
                                                                                                        1. To result
                                                                                                          1. For example
                                                                                                            1. Limiting value to a range
                                                                                                              1. from -1 to +1
                                                                                                              2. seting any negative values
                                                                                                                1. To zero
                                                                                                    2. Classification Decision
                                                                                                      1. Hidden Layer
                                                                                                        1. transform
                                                                                                          1. Input
                                                                                                            1. into
                                                                                                              1. Out put
                                                                                                          2. Does
                                                                                                            1. The hard work of classification
                                                                                                            2. Aply the BIAS
                                                                                                              1. A fixed value to sum or subtract
                                                                                                                1. Random
                                                                                                                  1. when a neural network is created
                                                                                                                    1. an algorithm goes in and starts tweaking
                                                                                                                      1. All those values to train the neural network
                                                                                                                        1. using
                                                                                                                          1. Label data
                                                                                                                            1. For training and testing
                                                                                                                              1. a process very much like Human learning
                                                                                                            3. were invented
                                                                                                              1. over fifty years ago
                                                                                                        Show full summary Hide full summary

                                                                                                        Similar

                                                                                                        How to Write a Program with the Seven Steps
                                                                                                        Luiz Porto
                                                                                                        Higher Level Economics
                                                                                                        Jim hammerton
                                                                                                        New Possibilities with ExamTime's Flashcard Maker
                                                                                                        Andrea Leyden
                                                                                                        Cell Structure
                                                                                                        megan.radcliffe16
                                                                                                        GCSE Maths Quiz: Ratio, Proportion & Measures
                                                                                                        Andrea Leyden
                                                                                                        Computer Systems
                                                                                                        lisawinkler10
                                                                                                        Test your Knowledge with Quizzes
                                                                                                        daniel.praecox
                                                                                                        Using GoConqr to study Maths
                                                                                                        Sarah Egan
                                                                                                        Biology - B1 - AQA - GCSE - Keeping Healthy and Defending Against Infection
                                                                                                        Josh Anderson
                                                                                                        Část 2.
                                                                                                        Gábi Krsková
                                                                                                        Diseño de Software
                                                                                                        Verny Fernandez