Create Machine and Deep Learning models, the technologies that are shaping our everyday lives and the decisions we make.
Machine Learning (ML) and Deep Learning (DL), as parts of Artificial Intelligence (AI), are the sciences that enhance the ability of developing intelligent machines in order to make decisions - from self-driving cars, speech and face recognition to medical diagnosis, bioinformatics, personalization, and time series forecasting.
Currently, Machine and Deep Learning is so a hot trend that it can be found to almost any aspect of your everyday life, from your mobile camera to your TV.
This course provides the fundamental principles of Machine and Deep Learning. It covers theoretical foundations as well as essential algorithms for supervised and unsupervised learning along with practical examples and assignments that concern the application of machine and deep learning to a range of real-world problems.
Anyone who wants to expand his/her current knowledge of AI or wants to adapt Machine and Deep Learning to his/her job in order to level up data analysis, forecasting and desicion making.
Take into consideration that Machine Learning is a mathematical discipline and it is desirable to have a good background in linear algebra and algorithms.
Furthermore, solid knowledge of Python and related data science libraries is required. Consider taking courses Programming with Python and Data Analysis and Visualization first if you are new to programming.
We enlist industry experts to plan, author and review our syllabus. It will guide you from fundamental concepts all the way to full scale implementations. It is constantly updated, and you get lifetime access.
Linear regression is used for predicting a real-valued output based on a series of input values. Linear regression can be applied to several applications such as housing price prediction or the temperature of an area. Here we will also present the notion of a cost function, and introduce the gradient descent method for learning.
Naive Bayes is one of the basic machine learning algorithm, widely used for classification problems. It works on the Bayes theorem of probability to predict the class of unknown datasets. In the same time, Decision Trees are the most widely and commonly used machine learning algorithms. They are used for solving both classification as well as regression problems being robust to Outliers.
The k-nearest neighbors (KNN) algorithm is a simple, easy-to-implement supervised machine learning algorithm that can be used to solve both classification and regression problems. It assumes that similar things exist in close proximity and uses the k-Nearest Neighbors of an object so to classify it.
Support Vector Machines (SVM) are one of the most powerful machine learning models around. During this week you will learn the theory behind the SVM by understanding hyperplanes and Kernel tricks to leave you with one of the most popular machine learning algorithms at your disposal.
The k-means clustering method is an unsupervised machine learning technique used to identify clusters of data objects in a dataset. It is considered to be one of the oldest and most approachable clustering method. Depending on the data size you will learn how to use both K-Means and Mini-Batch K-Means.
The human brain consists of 100 billion cells called neurons, connected together by synapses. If sufficient synaptic inputs fire to a neuron, that neuron will also fire. We call this process “thinking”. We can model this process by creating a neural network on a computer.
Convolutional Neural Networks (CNN) allow computers to see. In other words, CNNs are used to recognize images by transforming the original image through layers to a class scores. CNN was inspired by the visual cortex. Every time we see something, a series of layers of neurons gets activated, and each layer will detect a set of features such as lines, edges. The high level of layers will detect more complex features in order to recognize what we saw.
In order to handle sequential data successfully, you need to use a Recurrent Neural Network (RNN). It is able to “memorize” parts of the inputs and use them to make accurate predictions. These networks are at the heart of speech recognition, translation and more. Many sophisticated software products are using RNNs, like Google Translate and Apple Siri.