Computer science algorithm.

1. Values that usefully
   1. Characterize
      1. Things
         1. we whish to clasify
2. Example
   1. Moth Clasifier
      1. 2 -Features
         1. Wingspan
         2. Mass
      2. Training Data
         1. Entomologist
            1. Colect Data to process
               1. Luna
               2. Emperor moths
               3. 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.
3. Represent lines in graphs
   1. X
      1. WingSpan
      2. Space
   2. Y
      1. Mass
      2. Time
4. used to
   1. plot Data
      1. overlap
         1. Meaning
            1. To have something in comon
            2. TO ocupy the same area in part
         2. Machine Learn Algorithm
            1. Find Optimal
               1. Seplaratkon
               2. Clasification
               3. 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

1. Some especialist
   1. Colect & Organize
      1. Data

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.

1. from other cells

1. using
   1. Signals
      1. Electrical
      2. chemical

Annotations:

• Rather than beig electrical or chemical signals, artificial neurons take numbers in and spit numbers out.

1. organize and analyze features
   1. Spit out the information

1. X-axis
   1. Wing Span
   2. Space
2. Y-axis
   1. Mass
   2. Time

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

1. Input
   1. into
      1. Out put

1. The hard work of classification

1. A fixed value to sum or subtract
2. 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