What you'll learn:
- Create multilayer perceptrons and use them for predictions
- Build and train probabilistic neural networks
- Build and train generalized regression neural networks
- Build and train recurrent neural networks
- Use recurrent neural networks for time series forecasting
Neural networks are powerful predictive tools that can be used for almost any machine learning problem with very good results. If you want to break into deep learning and artificial intelligence, learning neural networks is the first crucial step.
This is why I’m inviting you to an exciting journey through the world of complex, state-of-the-art neural networks. In this course you will develop a strong understanding of the most utilized neural networks, suitable for both classification and regression problems.
The mathematics behind neural networks is particularly complex, but you don’t need to be a mathematician to take this course and fully benefit from it. We will not dive into complicated maths - our emphasis here is on practice. You will learn how to operate neural networks using the R program, how to build and train models and how to make predictions on new data.
All the procedures are explained live, on real life data sets. So you will advance fast and be able to apply your knowledge immediately.
This course contains four comprehensive sections.
1. Multilayer Perceptrons – Beyond the Basics
Learn to use multilayer perceptrons to make predictions for both categorical and continuous variables. Moreover, learn how to test your models accuracy using the k-fold cross-validation technique and how improve predictions by manipulating various parameters of the network.
2. Probabilistic Neural Networks
These networks are primarily used for classification problems, so we’ll learn how to predict a bank’s customers default with their help. Next, we’ll see how to look for optimal values of the smoothing parameter in order to make more accurate predictions.
3. Generalized Regression Neural Networks
If you have to solve a regression problem (where your response variable is numeric), these networks can be very effective. We’ll show how to predict a car value based on its technical characteristics and how to improve the prediction by controlling the smoothing parameter of our model. The k-fold cross-validation techniques will also be employed to identify better models.
4. Recurrent Neural Networks
These networks are useful for many prediction problems, but they are particularly valuable for time series modelling and forecasting. In this course we focus on two types of recurrent neural networks: Elman and Jordan. We are going to use them to predict future air temperatures based on historical data. Making truthful predictions on time series is generally very tough, but we will do our best to build good quality models and get satisfactory values for the prediction accuracy metrics.
For each type of network, the presentation is structured as follows:
a short, easy to understand theoretical introduction (without complex mathematics)
how to train the network in R
how to test the network to make sure that it does a good prediction job on independent data sets.
For every neural network, a number of practical exercises are proposed. By doing these exercises you’ll actually apply in practice what you have learned.
This course is your opportunity to become a neural network expert in a few days only (literally). With my video lectures, you will find it very easy to master these major neural network and build them in R. Everything is shown live, step by step, so you can replicate any procedure at any time you need it.
So click the “Enroll” button to get instant access to your course. It will surely get you some new, valuable skills. And, who knows, it could greatly enhance your future career.
See you inside!