Sei sulla pagina 1di 4

Introduction: examples; data-to-knowledge; assumptions; the model; inference paradigm;

inference engine; the data; the problem of induction


The linear model & least-squares: some useful results; formulation; solution; operation;
Matlab example
Non-linearity & MIMO problems: generalization of the linear model; univariate non-linear
functions; Matlab example; functions of more than on variable; colinearity; multi-response
Non-linear MISO relationships: non-linear input/output functions of more than one variable;
Matlab example; other choices of basis
LIP modelling with basis functions: model building; radial basis functions; sigmoidal basis
functions
Controlling complexity: choices; regularization; Matlab example; parsimony
Model selection: cross-validation; a strategy
Gradient-based optimization: motivation; first-order approximation; stability; convexity
Non-linear models: overview; neural networks; the multi-layer Perceptron; Netlab
The data: sample size & distribution; the “small-sample-size” problem; normalization; time
signals
Pattern recognition: overview; classification; logistic regression; decision making
Non-linear classification: generalization; non-linear models; assessment of performance
More recent approaches to modelling and inference
Introduction to deep-learning

This course provides a broad introduction to machine learning, datamining, and statistical
pattern recognition. Topics include: (i) Supervised learning (parametric/non-parametric
algorithms, support vector machines, kernels, neural networks). (ii) Unsupervised learning
(clustering, dimensionality reduction, recommender systems, deep learning). (iii) Best
practices in machine learning (bias/variance theory; innovation process in machine learning
and AI). The course will also draw from numerous case studies and applications, so that
you'll also learn how to apply learning algorithms to building smart robots (perception,
control), text understanding (web search, anti-spam), computer vision, medical informatics,
audio, database mining, and other areas.
Machine learning is changing the way we design and use our technology. It has slowly spread
it’s reach through our devices, from self-driving cars to even automated chatbots. To define
machine learning in the simplest terms, it is basically the ability to equip computers to think
for themselves based on the scenarios that occur. This is the basis of artificial intelligence.

With machine learning as the future of technology, getting your hands on this type of
development is crucial. However, it isn’t easy. Machine learning is a complex concept that
uses algorithms to design coding that will help the computers decipher a lot of data. This is
why we have designed this course. If you are interested in mastering machine learning using
a simple and easy approach, then this course is for you!

The only requisites for this course includes having a strong mathematical background and
familiarity with Python coding principles. Everything else is provided within this course.
Starting at the very beginning, this course will help you breakdown machine learning into
simple and easy to understand concepts.

The course covers a variety of different machine learning concepts such as supervised
learning, unsupervised learning, reinforced learning and even neural networks. But that’s not
all. In addition to understanding the theory behind machine learning, you will then actually
use these concepts and implement them into actual projects to see how they work in action!

The course also comes with quizzes at the end of each section to help solidify your
understanding for the subject. It will also help you valuate your learning of the subject.

At the end of this interactive and hands-on course, you will have everything you need to
actually get started with understanding machine learning algorithms and even start writing
your own algorithms that you can use for your own projects.

Let’s take a look at everything you will find in this course.

What you will learn in this course:

 What is machine learning


 Breakdown of important concepts required in machine learning
 Different types of machine learning
 Detailed analysis of the different types of machine learning such as unsupervised
learning, supervised learning, reinforcement learning, neural networks, and so on
 How to integrate the algorithms in actual Python Projects
 Quizzes at the end of each unit to help evaluate your learning
 If you want and easy introduction into machine learning, then this course has got you
covered. It has been designed to help newbies understand exactly what is machine
learning and how to get started with machine learning
Section 1 : An Introduction to Machine Learning

1 - Introduction

2 - What is Machine Learning

3 - Types and Applications of ML

4 - AI vs ML

5 - Essential Math for ML and AI

Section 2 : Supervised Learning - Part 1

6 - Introduction to Supervised Learning

7 - Linear Methods for Classification

8 - Linear Methods for Regression

9 - Support Vector Machines

10 - Basis Expansions

11 - Model Selection Procedures

12 - Bonus! Supervised Learning Project in Python Part 1

13 - Bonus! Supervised Learning Project in Python Part 2

Section 3 : Unsupervised Learning

14 - Introduction to Unsupervised Learning

15 - Association Rules

16 - Cluster Analysis

17 - Reinforcement Learning

18 - Bonus! KMeans Clustering Project

Section 4 : Neural Networks

19 - Introduction to Neural Networks

20 - The Perceptron

21 - The Backpropagation Algorithm


22 - Training Procedures

23 - Convolutional Neural Networks

Section 5 : Real World Machine Learning

24 - Introduction to Real World ML

25 - Choosing an Algorithm

26 - Design and Analysis of ML Experiments

27 - Common Software for ML

Section 6 : Final Project

Potrebbero piacerti anche