Practical Machine Learning with TensorFlow 2.0 and Scikit-Learn

Focused View

Samuel Holt

10:27:29

11 View

1.Installing Scikit-Learn and TensorFlow 2.0

01.Course Overview.mp4

03:52

02.Overview of the Anaconda Distribution.mp4

05:34

03.Installing the Anaconda Distribution for Scikit-Learn.mp4

06:15

04.Installing TensorFlow 2.0 from the Anaconda Distribution.mp4

04:20

05.Install Scikit-Learn and Tensorflow 2.0 Manually Through pip.mp4

03:07

2.ML Fundamentals - Scikit-Learn Introduction

06.What Is Machine Learning.mp4

09:31

07.First Scikit-Learn Model.mp4

07:37

08.Overfitting and Regularization.mp4

10:00

09.Probability and Statistics Review.mp4

15:00

10.Probability Distribution and Metrics.mp4

14:50

3.Applied Scikit-Learn - Supervised Learning Models

11.Supervised Learning and KNN.mp4

10:09

12.Logistic Regression.mp4

13:31

13.Naive Bayes.mp4

09:43

14.Support Vector Machines.mp4

11:49

15.Decision Trees.mp4

15:31

16.Ensemble Methods.mp4

20:59

4.Unsupervised Learning

17.K-means and Hierarchical Clustering.mp4

12:08

18.Connectivity and Density Clustering.mp4

12:55

19.Gaussian Mixture Models.mp4

07:32

20.Variational Bayesian Gaussian Mixture Models.mp4

08:46

21.Decomposing Signals into Components.mp4

08:55

22.Signal Decomposition with Factor and Independent Component Analysis.mp4

10:01

23.Novelty Detection.mp4

06:51

24.Outlier Detection.mp4

07:47

25.Locally Linear Embedded Manifolds.mp4

11:38

26.Multi-Dimensional Scaling and t-SNE Manifolds.mp4

12:01

27.Density Estimation.mp4

08:46

28.Restricted Boltzmann Machine.mp4

12:52

5.TensorFlow 2.0 Essentials for ML

29.TensorFlow 2.0 Overview.mp4

13:13

30.TensorFlow 2.0s Gradient Tape.mp4

08:48

31.Working with Neural Networks and Keras.mp4

13:25

32.Keras Customization.mp4

08:55

33.Custom Networks in Keras.mp4

06:55

34.Core Neural Network Concepts.mp4

13:25

35.Regression and Transfer Learning.mp4

07:50

36.TensorFlow Estimators and TensorBoard.mp4

09:37

6.Applied Deep Learning for Computer Vision Tasks

37.Introduction to ConvNets.mp4

08:30

38.ConvNets In Keras.mp4

07:28

39.Image Classification with Data Augmentation.mp4

07:44

40.Convolutional Autoencoders.mp4

07:38

41.Denoising and Variational Autoencoders.mp4

07:22

42.Custom Generative Adversarial Networks.mp4

08:25

43.Semantic Segmentation.mp4

06:32

44.Neural Style Transfer.mp4

09:49

7.Natural Language Processing and Sequential Data

45.Using Word Embeddings.mp4

09:49

46.Text Pipeline with Tokenization for Classification.mp4

11:22

47.Sequential Data with Recurrent Neural Networks.mp4

12:05

48.Best Practices with Recurrent Neural Networks.mp4

06:24

49.Time Series Forecasting.mp4

09:47

50.Forecasting with CNNs and RNNs.mp4

07:42

8.Applied Sequence to Sequence and Transformer Models

51.NLP Language Models.mp4

11:39

52.Generating Text from an LSTM.mp4

09:39

53.Sequence to Sequence Models.mp4

07:55

54.MT Seq2Seq with Attention.mp4

09:30

55.NLP Transformers.mp4

11:39

56.Training Transformers and NLP In Practice.mp4

12:06

9.Working with Reinforcement Learning

57.Basics of Reinforcement Learning.mp4

13:45

58.Training a Deep Q-Network with TF-Agents.mp4

13:38

59.TF-agents In Depth.mp4

13:00

60.Value and Policy Based Methods.mp4

13:13

61.Exploration Techniques and Uncertainty In RL.mp4

13:16

62.Imitation Learning and AlphaZero.mp4

13:24

Description

Have you been looking for a course that teaches you effective machine learning in scikit-learn and TensorFlow 2.0? Or have you always wanted an efficient and skilled working knowledge of how to solve problems that can't be explicitly programmed through the latest machine learning techniques? If you're familiar with pandas and NumPy, this course will give you up-to-date and detailed knowledge of all practical machine learning methods, which you can use to tackle most tasks that cannot easily be explicitly programmed; you'll also be able to use algorithms that learn and make predictions or decisions based on data. The theory will be underpinned with plenty of practical examples, and code example walk-throughs in Jupyter notebooks. The course aims to make you highly efficient at constructing algorithms and models that perform with the highest possible accuracy based on the success output or hypothesis you've defined for a given task. By the end of this course, you will be able to comfortably solve an array of industry-based machine learning problems by training, optimizing, and deploying models into production. Being able to do this effectively will allow you to create successful prediction and decisions for the task in hand (for example, creating an algorithm to read a labeled dataset of handwritten digits). The code bundle for this course is available at https://github.com/PacktPublishing/Practical-Machine-Learning-with-TensorFlow-2.0-and-Scikit-Learn

More details

User Reviews

Rating

average 0

Total votes0

Focused display

Machine Learning

TensorFlow

Samuel Holt

Instructor's Courses

Samuel Holt has several years' experience implementing, creating, and putting into production machine learning models for large blue-chip companies and small startups (as well as within his own companies) as a machine learning consultant. He has machine learning lab experience and holds an MEng in Machine Learning and Software Engineering from Oxford University, where he won four awards for academic excellence. Specifically, he has built systems that run in production using a combination of scikit-learn and TensorFlow involving automated customer support, implementing document OCR, detecting vehicles in the case of self-driving cars, comment analysis, and time series forecasting for financial data.

PacktPub

View courses PacktPub

Packt is a publishing company founded in 2003 headquartered in Birmingham, UK, with offices in Mumbai, India. Packt primarily publishes print and electronic books and videos relating to information technology, including programming, web design, data analysis and hardware.