Get Instant Help From 5000+ Experts For
question

Writing: Get your essay and assignment written from scratch by PhD expert

Rewriting: Paraphrase or rewrite your friend's essay with similar meaning at reduced cost

Editing:Proofread your work by experts and improve grade at Lowest cost

And Improve Your Grades
myassignmenthelp.com
loader
Phone no. Missing!

Enter phone no. to receive critical updates and urgent messages !

Attach file

Error goes here

Files Missing!

Please upload all relevant files for quick & complete assistance.

Guaranteed Higher Grade!
Free Quote
wave
ENSC 413 Programming

You have been asked by your AI-startup to develop a classifier for pair-wise classification of input images of numbers (digits). The input to the program is two integers, between 0 and 9, and your task is to deliver a logistic-regression classifier for this pair of numbers given as input and report its classification accuracy.1.a:Using the digits database containing 1797 images, each of size 8x8 pixels (see link below), flatten each image into a vector of 64 pixels, and use these as training database to develop an algorithm that usesstochastic gradient descent with some mini-batch size and code-up the gradient descent yourself including regularization of the parameters to control complexity.1.b: Identify all the hyperparameters, and detail a strategy to learn the best values for these. Plot the weights and bias of the logistic neuron over the course of training (a representative sample). Present the necessary plots to convince your team manager that the training was successful.1.c: Report the accuracy/sensitivity(recall)/specificity/precision/F-scoreon a test dataset.1.d: Discuss the tradeoff between bias and variance as it pertains to this problem, and identify when you know which is occurring.2) Code up logistic regression using MNIST database again for a pair of input digits, including regularization of model weights using any/all library functions, and report the best performance for three choices of regularization (no regularization, medium amount of regularization and high regularization).Discuss the bias/variance tradeoff.

support
Whatsapp
callback
sales
sales chat
Whatsapp
callback
sales chat
close