Get to grips with TensorFlow 2.0 and scikit-learn
About This Video
Get to grips with TensorFlow 2.0 and scikit-learn
About This Video
In Detail
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).
Aidience
This course is for developers who are familiar with pandas and NumPy concepts and are keen to develop their machine learning methodologies and practices effectively using scikit-learn and TensorFlow 2.0.
Requirement:Prior Python programming knowledge is mandatory for this course.
Chapter 1 : Installing Scikit-Learn and TensorFlow 2.0
Course Overview
Overview of the Anaconda Distribution
Installing the Anaconda Distribution for Scikit-Learn
Installing TensorFlow 2.0 from the Anaconda Distribution
Install Scikit-Learn and Tensorflow 2.0 Manually Through pip
Chapter 2 : ML Fundamentals: Scikit-Learn Introduction
What Is Machine Learning?
First Scikit-Learn Model
Overfitting and Regularization
Probability and Statistics Review
Probability Distribution and Metrics
Chapter 3 : Applied Scikit-Learn: Supervised Learning Models
Supervised Learning and KNN
Logistic Regression
Naïve Bayes
Support Vector Machines
Decision Trees
Ensemble Methods
Chapter 4 : Unsupervised Learning
K-means and Hierarchical Clustering
Connectivity and Density Clustering
Gaussian Mixture Models
Variational Bayesian Gaussian Mixture Models
Decomposing Signals into Components
Signal Decomposition with Factor and Independent Component Analysis
Novelty Detection
Outlier Detection
Locally Linear Embedded Manifolds
Multi-Dimensional Scaling and t-SNE Manifolds
Density Estimation
Restricted Boltzmann Machine
Chapter 5 : TensorFlow 2.0 Essentials for ML
TensorFlow 2.0 Overview
TensorFlow 2.0’s Gradient Tape
Working with Neural Networks and Keras
Keras Customization
Custom Networks in Keras
Core Neural Network Concepts
Regression and Transfer Learning
TensorFlow Estimators and TensorBoard
Chapter 6 : Applied Deep Learning for Computer Vision Tasks
Introduction to ConvNets
ConvNets In Keras
Image Classification with Data Augmentation
Convolutional Autoencoders
Denoising and Variational Autoencoders
Custom Generative Adversarial Networks
Semantic Segmentation
Neural Style Transfer
Chapter 7 : Natural Language Processing and Sequential Data
Using Word Embeddings
Text Pipeline with Tokenization for Classification
Sequential Data with Recurrent Neural Networks
Best Practices with Recurrent Neural Networks
Time Series Forecasting
Forecasting with CNNs and RNNs
Chapter 8 : Applied Sequence to Sequence and Transformer Models
NLP Language Models
Generating Text from an LSTM
Sequence to Sequence Models
MT Seq2Seq with Attention
NLP Transformers
Training Transformers and NLP In Practice
Chapter 9 : Working with Reinforcement Learning
Basics of Reinforcement Learning
Training a Deep Q-Network with TF-Agents
TF-agents In Depth
Value and Policy Based Methods
Exploration Techniques and Uncertainty In RL
Imitation Learning and AlphaZero