Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

Ultimate Neural Nets and Deep Learning Masterclass in Python

Name: Ultimate Neural Nets and Deep Learning Masterclass in Python
Rating: 4.3 (72 reviews)

The best way to learn machine learning and AI using python: simply and fully explained concepts with practical exercises

Created byJohn Harper

Last updated 2/2019

English

What you'll learn

Confidently code neural nets
Create your own machine learning programs
Able to construct AI architectures
You will have a full portfolio to maximise your employability
An understanding of the overlying strategies for solving real world problems
Knowledgable in ways that you can monetise your new skill
Fully able to code image classifiers from scratch
A fundamental understanding of the underlying mathematical concepts

Course content

9 sections • 52 lectures • 6h 36m total length

About the course1:59
How to maximise your learning4:03
Maximize learning by using active memory, completing the first five lectures to gain momentum, and combining a learning notepad with code-along notebooks for hands-on neural networks.

What is deep learning, machine learning, AI?11:03
Real world applications of neural nets13:01
Linear regression7:44
Line of best fit10:20
Linear regression with big data5:09
Overfitting, training and evaluation data6:47
Cost and loss9:34
How neural nets learn5:08
Explore how neural nets learn by extending linear regression, initializing weights and biases, and minimizing loss (mean squared error) with activation functions to fit data.

Neural networks recap20:27
Training wheels off - linear regression to neural nets13:33
Explore how neural networks process inputs through hidden layers to produce outputs using nodes with linear regression and weights, then apply activation functions like sigmoid to introduce nonlinearity and learning.
Adding an activation function5:43
*Milestone - First neural network*15:28
Multiple inputs5:59
Hidden layers4:37
Hidden layers in fully connected networks add complexity to reveal hidden data patterns. Weights, biases, and activation functions connect inputs and outputs, increasing computation and the risk of overfitting.
Your neural network learning, back propagation12:41

'Hello world' for tensorflow6:02
Feeding data and running sessions8:06
Data structures3:31
Learn how images are structured for neural networks, using height, width, and depth (rgb), batches of images, and four-dimensional tensors with TensorFlow placeholders and tf.reshape.
Loading data into tensorflow12:14
Loading data part 27:20
Learn to load image data into x and y with aligned indices, split into train and test sets, and set up placeholders for 100×100 color images with one-hot labels.
One hot encoding2:42
Learn one hot encoding and its role in classification versus regression, using examples like yes/no or bird, cat, dog, and see how positive and negative indicators shape model inputs.
Neural network - let's go!8:17
Give your network a brain - backpropagation, loss and optimiser14:57
Running your model8:48
Using other frameworks3:25

Loading handwritten digits using Keras7:39
Creating the model4:45
Define a sequential neural network for handwritten digit classification by building a dense 784-length input layer, applying ReLU activations, softmax output, and compiling with cross-entropy loss using Adam, assessing accuracy.
Running your model9:50
Run a neural network with four lines of code to fit data, evaluate on test data, and report final accuracy, illustrating normalization and one-hot encoding in digit recognition.

What are CNNs? how are they useful?9:08
How do CNNs work6:11
Filters15:15
Learn how convolutional filters abstract basic features from images using kernels, stride, and zero padding. See how output depth equals the number of filters and how to compute output dimensions.
Pooling5:13
One full forward pass21:56
Hyperparameters of CNNs3:32
Explore the hyperparameters of convolutional neural networks, including filter size, number of filters, stride, padding, activation function, and pooling, and see how choices shape feature extraction and edge handling.
Practical #1 - Image classifier using Tensorflow1:39
Preparing the data8:26
Creating the CNN architecture9:12
Adding the 'brain'12:13
Develop and train a neural network brain by preparing data, building the architecture, and applying softmax with cross-entropy loss, then optimize with Adam to evaluate accuracy and a confusion matrix.
Running your model10:21
Runs a convolutional neural network on a small image dataset, detailing data prep, a 3x3 conv layer with relu, pooling, and training to improve accuracy using a confusion matrix.

Requirements

You should have a basic knowledge of Python. You can check my other course on python.
A computer preferably no older than 5-7 years old.
No experience with maths or data science required.

Description

USED BY SOFTWARE STUDENTS AT CAMBRIDGE UNIVERSITY - WORLD CLASS DEEP LEARNING COURSE - UPDATED CONTENT January 2018

Master practical deep learning and neural network concepts and fundamentals

My course does exactly what the title describes in a simple, relatable way. I help you to grasp the complete start to end concepts of fundamental deep learning.

Why you need this course

Coming to grips with python isn't always easy. On your own it can be quite confusing, difficult and frustrating. I've been through the process myself, and with the help of lifelong ... I want to share this with my fellow beginners, developers, AI aspirers, with you.

What you will get out of this course

I will give you straightforward examples, instructions, advice, insights and resources for you to take simple steps to create your own neural networks from scratch. By the end of the course you will be able to create neural networks to create your very own image classifier, able to work on your own images.

I personally provide support within the course, answering questions and giving feedback on what you're discovering/creating along the way. I don't just throw you in at the deep end - I provide you with the resources to learn and develop what you need at a pace to work for you and then help you stroll through to the finish line. Studies have shown that to learn effectively from online courses tutorials should last around ten minutes each. Therefore to maximise your learning experience all of the lectures in this course have been created around this amount of time.

My course integrates all of the aspects required to get you on the road becoming a successful deep learning developer. I teach and I preach, with live, practical exercises and walkthroughs at the end of each section!

Why this price?

As a professional AI developer I have over five years in Senior positions in software development and technology entrepreneurship, with experience in tutoring and creating online courses, catering to thousands of students. Face to face I charge $50 per hour for a student. To complete the curriculum that I offer it would cost them between $500 - $1000.

To reach more people than I could face to face I decided to create this course. As I add more content I intend to raise the price but for now I've decided on this price - the cost of around just three lessons.

By paying a small cost for this course I believe you will get your value back, with a lot more by the time you have completed it.

Ask yourself - how much is mastering the fundamentals of python (and setting up your skills for AI engineering) worth to you?

How long will it take?

Although everyone is different, on average it has taken existing students between 4 - 6 weeks to complete the course, whilst developing their skills and knowledge along the way.

Who this is not for

This course is not for anyone looking for a one-click fix. Although I provide you with a path walked enough times that it can be a relatively smooth journey it still requires a lot of time and effort from you to make it happen. If you're not interested in putting in your energy to truly better yours skills in python then this may not be the right course for you.

Is there a money back guarantee if I'm not happy?

Absolutely. I am confident that my course will bring you more value than you spend on the course. As one of the previously top featured Udemy Instructors my motto is 'your success is my success'. If within the first 30 days you feel my course is not going to help you to achieve your goals in python programming then you get a no questions asked, full discount.

What materials are included?

The majority of my lectures I have chosen to be in video format so that you can hear and see me when we're going through each and every area of the course.

Aswell as the course lectures, presentations, scripts and quizzes the course will soon also offers my full support as an instructor to answer questions, provide feedback and support

I will be constantly adding more valuable content and resources to the course as time goes by. Keep checking back here if you're not sure right now and feel free to send me a message with any questions or requests you may have.

So go ahead and click the 'Take this course' button at the top right of your screen. I look forward to seeing you on the course.

Who this course is for:

Any of the following:
Anyone with an interest in machine learning
Those familiar with python and looking to level up their skills
Those coming from a mathematical or engineering background

Ultimate Neural Nets and Deep Learning Masterclass in Python

What you'll learn

Explore related topics

Course content

About the course2 lectures • 6min

The basic theory8 lectures • 1hr 9min

Neural networks - the theory7 lectures • 1hr 18min

Setting up your computer4 lectures • 20min

The fun stuff - creating your first neural network10 lectures • 1hr 15min

Portfolio project #1 - Creating an image classifier using Keras3 lectures • 22min

Hyperparameters and bias4 lectures • 17min

Conclusions3 lectures • 6min

Convolutional neural networks - high power image classifiers11 lectures • 1hr 43min

Requirements

Description

Who this course is for: