Graphic design python turtle 🐢

from turtle import * import colorsys bgcolor('black') pensize(0) tracer(50) h=0 for i in range(300): c=colorsys.hsv_to_rgb(h,1,1) h+=0.9 color(c) forward(300) left(100) fd(i) goto(0,0) down() rt(90) begin_fill() circle(0) end_fill() rt(10) for j in range(5): rt(30) done() Please follow my blog and subscribe my channel for more videos and newly updates 👍👍👍👍👍 import turtle as t import colorsys t.bgcolor('black') t.tracer(100) h=0.4 def draw(ang,n): t.circle(5+n,60) t.left(ang) t.circle(5+n,60) for i in range(200): c=colorsys.hsv_to_rgb(h,1,1) h+=0.005 t.color(c) t.pensize(2) draw(90,i*2) draw(120,i*2.5) draw()

Back Propagation in machine learning

 Back Propagation

Back Propagation is the essence of neural net training. It is the practice of finetuning the weights of a neural net based on the error rate. obtained in the previous epoch. proper tuning of the weights ensures lower error rates, making the model model reliable by increasing its generalization.

Advantages

  1. The computing time is minimized if the weights chosen are small at the beginning.
  2. The mathematical formula of back propagation can be applied to any network.

Disadvantages
  1. It has more number of learning steps, and also the learning phase has intensive calculations.
  2. The training may sometimes cause temporal instability to  the system
  3. The network may get trapped in a local minima.

Applications
  1. Data compression
  2. Image compression
  3. Face recognition
  4. Optical character recognition
  5. Control problems
  6. Non-linear simulation
  7. Fault detection problem
  8. Load forecasting problem


















Comments

Popular posts from this blog

Create shape using python turtle 🐢

Make fire crackers using python turtle 🐢

Protocol verification using finite state machine model in computer network