Course Library View the full range of courses
Accounting (92 courses)
Language (58 courses)
Teaching & Education (37 courses)
Health and Social Care (136 courses)
Management (346 courses)
IT & Software (117 courses)
Employability (863 courses)
Personal Development (1332 courses)
Introduction to Deep Learning | |||
What is Deep Learning? | 00:03:00 | ||
Course Materials | 00:00:00 | ||
Why is Deep Learning Important? | 00:02:00 | ||
Software and Frameworks | 00:01:00 | ||
Artificial Neural Networks (ANN) | |||
Introduction – ANN | 00:01:00 | ||
Anatomy and function of neurons | 00:01:00 | ||
An introduction to the neural network | 00:03:00 | ||
The architecture of a neural network | 00:02:00 | ||
Propagation of information in ANNs | |||
Feed-forward and Back Propagation Networks | 00:01:00 | ||
Backpropagation In Neural Networks | 00:01:00 | ||
Minimising the cost function using backpropagation | 00:01:00 | ||
Neural Network Architectures | |||
Single-layer perceptron (SLP) model | 00:01:00 | ||
Radial Basis Network (RBN) | 00:01:00 | ||
Multi-layer perceptron (MLP) Neural Network | 00:01:00 | ||
Recurrent neural network (RNN) | 00:01:00 | ||
Long Short-Term Memory (LSTM) networks | 00:02:00 | ||
Hopfield neural network | 00:01:00 | ||
Boltzmann Machine Neural Network | 00:01:00 | ||
Activation Functions | |||
What is the Activation Function? | 00:02:00 | ||
Important Terminologies | 00:01:00 | ||
The sigmoid function | 00:02:00 | ||
Hyperbolic tangent function | 00:01:00 | ||
Softmax function | 00:01:00 | ||
Rectified Linear Unit (ReLU) function | 00:01:00 | ||
Leaky Rectified Linear Unit function | 00:01:00 | ||
Gradient Descent Algorithm | |||
What is Gradient Decent? | 00:02:00 | ||
What is Stochastic Gradient Decent? | 00:02:00 | ||
Gradient Decent vs Stochastic Gradient Decent | 00:01:00 | ||
Summary Overview of Neural Networks | |||
How do artificial neural networks work? | 00:04:00 | ||
Advantages of Neural Networks | 00:01:00 | ||
Disadvantages of Neural Networks | 00:01:00 | ||
Applications of Neural Networks | 00:02:00 | ||
Implementation of ANN in Python | |||
Introduction | 00:04:00 | ||
Exploring the dataset | 00:01:00 | ||
Problem Statement | 00:01:00 | ||
Data Pre-processing | 00:04:00 | ||
Loading the dataset | 00:02:00 | ||
Splitting the dataset into independent and dependent variables | 00:03:00 | ||
Label encoding using scikit-learn | 00:05:00 | ||
One-hot encoding using scikit-learn | 00:06:00 | ||
Training and Test Sets: Splitting Data | 00:04:00 | ||
Feature Scaling | 00:03:00 | ||
Building the Artificial Neural Network | 00:02:00 | ||
Adding the input layer and the first hidden layer | 00:03:00 | ||
Adding the next hidden layer | 00:01:00 | ||
Adding the output layer | 00:02:00 | ||
Compiling the artificial neural network | 00:03:00 | ||
Fitting the ANN model to the training set | 00:02:00 | ||
Predicting the test set results | 00:04:00 | ||
Convolutional Neural Networks (CNN) | |||
Introduction | 00:01:00 | ||
Components of convolutional neural networks | 00:01:00 | ||
Convolution Layer | 00:03:00 | ||
Pooling Layer | 00:02:00 | ||
Fully connected Layer | 00:02:00 | ||
Implementation of CNN in Python | |||
Dataset | 00:01:00 | ||
Importing Libraries | 00:02:00 | ||
Building the CNN model | 00:12:00 | ||
Accuracy of the model | 00:02:00 | ||
Order your Certificates & Transcripts | |||
Order your Certificates & Transcripts | 00:00:00 |
Can’t find the anwser you’re looking for ? Reach out to customer support team.
There are no specific prerequisites for this course, nor are there any formal entry requirements. All you need is an internet connection, a good understanding of English and a passion for learning for this course.
You have the flexibility to access the course at any time that suits your schedule. Our courses are self-paced, allowing you to study at your own pace and convenience.
For this course, you will have access to the course materials for 1 year only. This means you can review the content as often as you like within the year, even after you've completed the course. However, if you buy Lifetime Access for the course, you will be able to access the course for a lifetime.
Yes, upon successfully completing the course, you will receive a certificate of completion. This certificate can be a valuable addition to your professional portfolio and can be shared on your various social networks.
We want you to have a positive learning experience. If you're not satisfied with the course, you can request a course transfer or refund within 14 days of the initial purchase.
Our platform provides tracking tools and progress indicators for each course. You can monitor your progress, completed lessons, and assessments through your learner dashboard for the course.
If you encounter technical issues or content-related difficulties with the course, our support team is available to assist you. You can reach out to them for prompt resolution.