Machine Learning (ML) Bootcamp: Python, TensorFlow, Colab,..
2.9 (28 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
6,882 students enrolled

Machine Learning (ML) Bootcamp: Python, TensorFlow, Colab,..

Master the 3 M's of ML: Maths, Methods and Machine
2.9 (28 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
6,882 students enrolled
Created by Samuel Reischl
Last updated 9/2019
English
English [Auto]
Current price: $132.99 Original price: $189.99 Discount: 30% off
23 hours left at this price!
30-Day Money-Back Guarantee
This course includes
  • 5 hours on-demand video
  • 9 articles
  • 23 downloadable resources
  • Full lifetime access
  • Access on mobile and TV
  • Assignments
  • Certificate of Completion
Training 5 or more people?

Get your team access to 4,000+ top Udemy courses anytime, anywhere.

Try Udemy for Business
What you'll learn
  • The three building blocks of Machine Learning: Maths, Methods and Machine.
  • Maths: Calculus, Linear Algebra, Statistics, Naive Bayes
  • Methods: Neural Networks, Deep Learning, PCA, Scikit-learn, Tensorflow, Keras
  • Machine: Python, Cloud Computing, Colab
  • Insights into real life projects and how to apply the concepts
Course content
Expand all 48 lectures 04:53:08
+ Introduction & Overview
3 lectures 10:56
ML in a Nutshell
02:57
Solve the attached data science crossword puzzle and check what you already know about AI (artificial intelligence), ML (machine learning) and DS (data science).
Data Science crossword puzzle
1 question
Linear Regression
02:42
Collect all abbreviations and key concepts during the course and write them down.
Abbreviations & Concepts
1 question
+ Methods 0: Scikit-learn
5 lectures 44:09

Please find attached the IPython notebook.

Feel free to explore the code.

Data transformation and splitting
15:00
Estimators
09:25
Metrics
03:25

Please find attached the IPython notebook.

Feel free to explore the code.

Preview 07:44

Check your understand!

Quiz
4 questions
+ Project: Titanic (Binary Classification)
3 lectures 28:57
This project uses the Titanic dataset from Kaggle (https://www.kaggle.com/c/titanic/data). And here the training data file (train.csv).
Project Titanic overview
1 question
Titanic Dataset
10:21

Please find atached the full solution as IPython notebook.

Feel free to explore the code.

Data transformation and ML model
09:03
+ Project: Boston Housing (Regression)
1 lecture 11:29
In this project you use the Boston Housing data. The data was collected from homes in suburbs of Boston, Massachusetts, in 1978. Based on numeric data features (e.g. age, size and location) the value of a house shall be predicted.
Boston Housing tasks
3 questions

Please find attached the solution as IPython notebook.

Feel free to explore the code.

Boston Housing solution
11:29
+ Project: Student Performance (Binary Classification)
1 lecture 08:45
Use the Student Performance dataset from the UCI machine learning repository. It was collected from students in secondary education of two Portuguese schools. The data attributes include student grades, demographic, social and school related features. As target attribute the final grade is used.
Student Performance tasks
1 question

Please find attached the solution as IPython notebook.

Feel free to explore the code.

Student Performance solution
08:45
+ Methods 1: Neural Networks
5 lectures 50:28
Forwardpropagation
11:45
Write a code in Python for forwardpropagation.
Programming exercise on forwardpropagation
1 question
Backpropagation
10:20
Activation Functions
11:30
Loss Functions
07:41

Check your understanding regarding neural networks and their components.

Neural Networks
3 questions
+ Methods 2: Tensorflow
3 lectures 23:52
Implementing a neural network
05:21

Please find attached the IPython notebook.

Feel free to explore the code.

Example: MNIST Fashion
09:59

Test your understanding of Tensorflow and KERAS.

Tensorflow & KERAS
3 questions
+ Project: MNIST hand-written digits (DCGAN)
2 lectures 12:43

Please find attached further information.

Introduction to GAN, CNN and DCGAN
00:05
Create a Generative Adversarial Network with a generator and a discriminator based on neural networks that will create hand-written digits like the MINST standard data set from scratch.
Hand-written digits task
2 questions

Please find attached the solution as iPython notebook.

Feel free to explore the code.

DCGAN MINST solution
12:38

Test your understanding.

DCGAN
3 questions
+ Project: Stock market prediction (LSTM)
2 lectures 10:03

Please find attached the document.

Introduction to time series data, RNN and LSTM
00:05
Predict stock market prices with an Long Short-Term Memory (LSTM) recurrent neural network.
Stock market prediction task
2 questions

Please find attached the solution as iPython notebook.

Feel free to further explore the code.

LSTM solution
09:58

Test your understanding.

Time series data, RNN and LSTM
3 questions
+ Project: Language Translation (NMT)
2 lectures 07:52

Please find attached the document.

Introduction to Sequence-to-sequence (seq2seq) models
00:05
In this project we do build a German-English translation model. We implement a sequence to sequence (seq2seq) model, in particular an encoder-decoder model with attention (Bahdanau attention for the encoder). You will be able to input a German sentence, and return the English translation.
Language translation task
1 question

Please find attached the solution as iPython notebook.

Feel free to further explore the code.

NMT solution
07:47

Test your understanding.

Language translation
4 questions
Requirements
  • No prerequisites
Description

Do you want to master Machine Learning (ML) - the key field of the future?

ML is the core of artificial intelligence and will transform all industries and all areas of life.

This comprehensive course covers the three M's Maths, Methods and Machine, and is easy to understand.

Maths

  • Calculus

  • Linear Algebra

  • Probability theory

  • Statistics

Methods

  • Machine learning libraries

    • Scikit-learn

    • Tensorflow

    • Keras

  • Estimators & Predictors

    • Neural Network (Deep Learning)

    • Support Vector Machine

    • K-Nearest Neighbor

    • Decision Tree

    • and many more

  • Concepts & techniques

    • Principal Component Analysis (PCA)

    • Neural Machine Translation (NMT)

    • Long Short-Term Memory (LSTM)

    • Monte-Carlo Tree Search (MCTS)

    • Deep Convolutional Generative Adversarial Network (DCGAN)

    • and many more

Machine

  • Python

  • Cloud Computing

  • Colab Cloud Notebook

These three building blocks will give you the deep understanding of the subject.

Machine Learning

  • Supervised learning

    • Regression

    • Classification

  • Unsupervised learning

  • Reinforcement learning

Furthermore projects will provide insights into real life solutions.

Projects

  1. Titanic dataset (binary classification)

  2. Boston Housing dataset (regression)

  3. Student performance (binary classification)

  4. Hand-written digits (image recognition & generation)

  5. Stock market predictions

  6. Text recognition and language translation

  7. Autonomous driving (reinforcement learning)

  8. Mastering the game of GO (deep reinforcement learning)

  9. Segmentation of customer data (PCA)

  10. Spam detection (Bayes)

Do not hesitate and join the course. ML will transform your life!

This course is extraordinary, as it is easy to understand, and combines education with entertainment.

Learning should be exciting!

Who this course is for:
  • Everyone who is interested in machine learning and artificial intelligence.
  • Pupils, students, employees in all kind of roles, self-employed workers
  • You!