Udemy – Modern Deep Learning in Python 2021-4

Published on: 2022-01-16 23:01:14

Categories: 28

Description

Modern Deep Learning in Python is a comprehensive, project-based deep learning course in the Python programming language published by Udemy Academy. Python is a high-level programming language used in various fields such as data science, machine learning, deep learning and artificial intelligence. Based on this programming language, various libraries and frameworks have been developed, the most important of which are Tensorflow, Theano, Keras, PyTorch, CNTK and MXNet. In this course, you will be introduced to batch learning techniques and stochastic gradient descent. Using these two techniques, you can practice artificial neural network using a limited set of data and speed up the network learning and practice process.

his course covers many complex topics in the field of machine learning and deep learning, the most important of which are momentum, adaptive learning rate and techniques such as AdaGrad, RMSprop and Adam, techniques Mentioned dropout regularization and batch normalization and their implementation in Theano and TensorFlow libraries. These two libraries have unique advantages over other libraries in terms of net performance and speed. In these two libraries, the user can use the processing capacity of the graphics card to increase the processing speed. This training course is completely practical and project-oriented, and during the training process, you will use real data and datasets.

What you will learn in Modern Deep Learning in Python

Adding momentum to backpropagation for neural network development
Adaptive learning rates and related techniques such as AdaGrad, RMSprop and Adam
Elements of Theano Library such as variables and functions
Development of artificial neural network with Theano library
TensorFlow Library and its Benefits
Development of artificial neural network with TensorFlow library
MNIST dataset
Gradient descent optimization algorithm
Stochastic gradient descent
Implementation of dropout regularization technique in Theano and TensorFlow libraries
Implementation of batch normalization technique in Theano and TensorFlow libraries
Development of artificial neural networks with Keras, PyTorch, CNTK and MXNet

Course specifications

Publisher: Udemy
Instructors: Lazy Programmer Inc
Language: English
Level: Introductory to Advanced
Number of Lessons: 87
Duration: 11 hours and 15 minutes

Course topics on 2021/10

Modern Deep Learning in Python Content

Modern Deep Learning in Python Prerequisites

Be comfortable with Python, Numpy, and Matplotlib

If you do not yet know about gradient descent, backprop, and softmax, take my earlier course, Deep Learning in Python, and then return to this course.

Suggested Prerequisites:

Know about gradient descent

Probability and statistics

Python coding: if/else, loops, lists, dicts, sets

Numpy coding: matrix and vector operations, loading a CSV file

Know how to write a neural network with Numpy