نوشتن 2 برنامه در پایتون
پنج سال پیش منتشر شده
تعداد بازدید: 187
کد پروژه: 229641
شرح پروژه
- با سلام
2 برنامه باید در گوگل کولب نوشته شود و فایل گوگل کولب (یا هر فایل دیگری که برای اجرای برنامه نیاز است) به همراه کامنت گذاری کامل ارسال شود
مهلت انجام حداکثر 2 روز است. در صورتی که کد ایرادی داشته باشد، خطا دهد یا از کدهای اینترنت استفاده شده باشد (نباید کپی کرده باشید، فقط هم اسم متغیرها تغییر نکند، اما میتونید از کدهای در اینترنت ایده بگیرید)
توضیحات:
1) 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 uses stochastic 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-score on 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.
Logistic regression is described in many articles online, such as this one:
https://towardsdatascience.com/logistic-regression-using-python-sklearn-numpy-mnist-handwriting-recognition-matplotlib-a6b31e2b166a (Links to an external site.)
مهارت ها و تخصص های مورد نیاز
مهلت برای انجام
2روز
وضعیت مناقصه
بسته
درباره کارفرما
عضویت ده سال پیش
