Find online courses made by experts from around the world.
Take your courses with you and learn anywhere, anytime.
Learn and practice real-world skills and achieve your goals.
This course is about artificial neural networks. Artificial intelligence and machine learning are getting more and more popular nowadays. In the beginning, other techniques such as Support Vector Machines outperformed neural networks, but in the 21th century neural networks again gain popularity. In spite of the slow training procedure, neural networks can be very powerful. Applications ranges from regression problems to optical character recognition and face detection. In the first part of the course you will learn about the theoretical background of neural networks, later you will learn how to implement them. If you are keen on learning methods, let's get started!
Not for you? No problem.
30 day money back guarantee.
Learn on the go.
Desktop, iOS and Android.
Certificate of completion.
|Section 1: Introduction|
|Section 2: Neural Networks Introduction|
Axons and neurons in the human brainPreview
Modeling human brain
Artificial neurons - the model
Artificial neurons - activations functions
Artificial neurons - an example
Neural networks - the big picture
Applications of neural networks
|Section 3: Hopfield Neural Network|
Hopfield neural network introductionPreview
Hopfield network energyPreview
Hopfield neural network training and learning
Hopfield neural network problems
Hopfield neural network example
Hopfield network implementation I - utils
Hopfield network implementation II - matrix operations
Hopfield network implementation III - network
Hopfield network implementation IV - running the application
|Section 4: Neural Networks With Backpropagation Theory|
Feedforward neural networks
Optimization - cost function
Simplified feedforward network
Feedforward neural network topology
The learning algorithm
Gradient calculation I - output layer
Gradient calculation II - hidden layer
Applications of neural networks I - character recognition
Applications of neural networks II - stock market forecast
|Section 5: Single Perceptron Model|
Perceptron model training
Perceptron model implementation I
Perceptron model implementation II
Perceptron model implementation III
Trying to solve XOR problem
Conclusion: linearity and hidden layers
|Section 6: Backpropagation Implementation|
Structure of the feedforward network
Backpropagation implementation I - activation function
Backpropagation implementation II - NeuralNetwork
Backpropagation implementation III - Layer
Backpropagation implementation IV - run
Backpropagation implementation V - train
|Section 7: Logical Operators|
Logical operators introduction
Running the neural network: AND
Running the neural network: OR
Running the neural network: XOR
|Section 8: Iris Dataset|
About the Iris dataset
Constructing the neural network
Testing the neural network
|Section 9: Optical Character Recognition (OCR)|
Optical character recognition theory
Transform an image into numerical data
Creating the datasets
OCR with neural network
|Section 10: Source Code|
Get other courses for a discounted price!
My name is Balazs Holczer. I am from Budapest, Hungary. I am qualified as a physicist and later on I decided to get a master degree in applied mathematics. At the moment I am working as a simulation engineer at a multinational company. I have been interested in algorithms and data structures and its implementations especially in Java since university. Later on I got acquainted with machine learning techniques, artificial intelligence, numerical methods and recipes such as solving differential equations, linear algebra, interpolation and extrapolation. These things may prove to be very very important in several fields: software engineering, research and development or investment banking. I have a special addiction to quantitative models such as the Black-Scholes model, or the Merton-model. Quantitative analysts use these algorithms and numerical techniques on daily basis so in my opinion these topics are definitely worth learning.