+ 1

Help me out with my Machine Learning Project

I am a final year Cse student and I seek experts guidelines on the subject. I need some guidelines about the domain and a few examples of real world ML projects. Anyone willing to guide me in this? Suggest me some problems as well if possible. Thanks

28th Aug 2018, 4:18 PM
Çhandra_ƞhekar
Çhandra_ƞhekar - avatar
2 Answers
+ 9
I would suggest starting from the basics about what machine learning is as a discipline and what are the typical problems that can be solved using machine learning algorithms. https://www.sololearn.com/learn/714/?ref=app Real world projects are in abundance and some of them are publicly available for solving (often for real world money, too ;) -- for example at www.kaggle.com Anyway, start from the basics and if you need any assistance or guidance, write some more inquiries. For a final project at CS studies I've seen image recognition/computer vision, e-commerce product recommendation systems and chatbots, for example. Seem quite complete as projects and not too exhausting, at least to a 'working' level solution.
28th Aug 2018, 6:20 PM
Kuba SiekierzyƄski
Kuba SiekierzyƄski - avatar
+ 2
from __future__ import print_function, division from terminaltables import AsciiTable import numpy as np import progressbar from mlfromscratch.utils import batch_iterator from mlfromscratch.utils.misc import bar_widgets class NeuralNetwork(): """Neural Network. Deep Learning base model. Parameters: ----------- optimizer: class The weight optimizer that will be used to tune the weights in order of minimizing the loss. loss: class Loss function used to measure the model's performance. SquareLoss or CrossEntropy. validation: tuple A tuple containing validation data and labels (X, y) """ def __init__(self, optimizer, loss, validation_data=None): self.optimizer = optimizer self.layers = [] self.errors = {"training": [], "validation": []} self.loss_function = loss() self.progressbar = progressbar.ProgressBar(widgets=bar_widgets) self.val_set = None if validation_data: X, y = validat
28th Aug 2018, 6:52 PM
Massimiliano
Massimiliano - avatar