Machine Learning Masterclass (Office Elearning Menu)

Introductie

Machine Learning Masterclass E-Learning Training

Machine Learning Architects interpreteren realtime analyse van gegevens om de efficiëntie in alle bedrijfsdomeinen te automatiseren en te verhogen, en zo de weg vrij te maken voor zinvolle AI die van reactief naar voorspellend gaat. Deze reis zal je begeleiden in de overgang van een ML-programmeur naar een ML / DL-architectmeester via mechanismen zoals computertheorie.

Omschrijving

Dit leertraject, met meer dan 100 uur online content, is onderverdeeld in de volgende vier tracks:ML

ML Track 1: ML ProgrammerML Track 2: DL ProgrammerML Track 3: ML EngineerML Track 4: ML Architect

Track 1: Machine Learning ProgrammerIn this track of the machine learning journey, the focus is linear regression, computational theory, and training sets.

Cursusinhoud

NLP for ML with Python: NLP Using Python & NLTK

Course: 1 Hour, 3 Minutes

• Course Overview
• Uses and Challenges of NLP
• Terminologies and Steps of NLP
• Parsing Approach and Parser Types
• Corpus and Corpus Linguistic
• Regular Expressions in Python
• NLP Libraries
• NLTK Setup
• Components of NLP
• Tokenization
• Tokenization with NLTK
• Stop Words with NLTK
• Exercise: NLP Terminologies and Stopworks

NLP for ML with Python: Advanced NLP Using spaCy & Scikit-learn

Course: 41 Minutes

• Course Overview
• Stemming and Lemmatization
• Synonyms and Antonyms with NLTK
• Topic Extraction with LDA
• NER and Standard Libraries
• POS Tagging and NLTK Implementations
• spaCy Framework
• Analyzing and Processing Texts
• Text Classification Using scikit-learn
• Sentiment Analysis
• Exercise: Sentiment Analysis with scikit-learn

Linear Algebra and Probability: Fundamentals of Linear Algebra

Course: 1 Hour, 41 Minutes

• Course Overview
• Linear Algebra and Machine Learning
• Class of Spaces
• Types of Vector Space
• Linear Product Vector and Theorems
• Vector Arithmetic
• Vector Scalar Multiplication
• Vector Norms
• Matrix Arithmetic
• Working with Matrix
• Matrix Operations
• Matrix Decomposition
• Exercise: Vector Norms and Matrix Arithmetic

Linear Algebra & Probability: Advanced Linear Algebra

Course: 1 Hour, 44 Minutes

• Course Overview
• Matrix and PCA
• Sparse Matrix
• Tensor Arithmetic
• Hadamard Product and Tensors
• Singular-Value Decomposition
• Reconstruct Rectangular Matrix Using SVD
• Probability
• Probability Basics and Propositions
• Random Variable
• Central Limit Theorem
• Parameter Estimation and Gaussian Distribution
• Binomial Distribution
• Exercise: Tensor Arithmetic and Hadamard Product

Linear Regression Models: Introduction to Linear Regression

Course: 1 Hour, 19 Minutes

• Course Overview
• Statistical Tools and Regression
• Reasons to Use Regression
• Regression Loss: Least Square Error
• Capturing Variance in Regression
• Prediction Using Regression
• Introduction to Deep Learning
• The Architecture of Neural Networks
• Neurons: The Building Blocks of a Neural Network
• Linear Regression Using a Single Neuron
• Training a Neural Network
• Gradient Descent Optimization
• Exercise: Introduction to Linear Regression

Linear Regression Models: Building Simple Regression Models with Scikit Learn and Keras

Course: 42 Minutes

• Course Overview
• Statistical Tools and Regression
• Reasons to Use Regression
• Regression Loss: Least Square Error
• Capturing Variance in Regression
• Prediction Using Regression
• Introduction to Deep Learning
• The Architecture of Neural Networks
• Neurons: The Building Blocks of a Neural Network
• Linear Regression Using a Single Neuron
• Training a Neural Network
• Gradient Descent Optimization
• Exercise: Introduction to Linear Regression

Linear Regression Models: Multiple and Parsimonious Linear Regression

Course: 1 Hour, 11 Minutes

• Course Overview
• Understanding Multiple Regression
• Kitchen Sink Regression
• Training and Evaluating the Model
• Preparing Data for a Neural Network
• Building a Neural Network
• Evaluating the Neural Network
• Finding Correlations in a Dataset
• Introducing Parsimonious Regression
• Applying Parsimonious Regression with Scikit Learn
• Exercise: Multiple Linear Regression

Linear Regression Models: An Introduction to Logistic Regression

Course: 58 Minutes

• Course Overview
• Introducing Logistic Regression
• The Logistic Regression Curve
• Logistic Regression and Classification
• Logistic Regression vs. Linear Regression
• Logistic Regression in Keras
• Preparing Data for Logistic Regression
• Classification using a Logistic Regression Model
• Preparing Data for a Neural Network
• Building and Evaluating the Keras Classifier
• Exercise: An Introduction to Logistic Regression

Linear Regression Models: Simplifying Regression and Classification with Estimators

Course: 36 Minutes

• Course Overview
• Introducing Estimators
• Preparing Data for a Linear Regressor Estimator
• Training and Evaluating a Regressor Estimator
• Preparing Data for a Linear Classifier Estimator
• Training and Evaluating a Classifier Estimator
• Exercise: Using TensorFlow Estimators

Computational Theory: Language Principle & Finite Automata Theory

Course: 45 Minutes

• Course Overview
• Theory of Computation
• Computation Models
• Automata Theory and Classes
• Principles of Finite State Machine
• Principles of Formal Languages and Automata Theory
• Elements of Formal Language
• Regular Expressions
• Regular Grammar
• Closure Properties of Regular Languages
• Context-Free Grammar Features
• Exercise: Computation Theory and Formal Language

Computational Theory: Using Turing, Transducers, & Complexity Classes

Course: 47 Minutes

• Course Overview
• Analytical Capabilities of Grammar
• Normal Forms in Context-Free Grammar
• Pushdown Automata
• Turing Machines
• Turing Machine Themes
• Finite Transducers Types
• Computation Limitations
• Computational Complexity
• P and NP Class
• Recursively Enumerable Languages
• Exercise: Turing Machines and Finite Transducers

Model Management: Building Machine Learning Models & Pipelines

Course: 32 Minutes

• Course Overview
• Machine Learning Algorithms and Models
• Machine Learning Model Types
• Machine Learning Model Development
• Creating and Saving ML Models with scikit-learn
• Models for Regression and Classification Management
• Building Machine Learning Pipelines
• Machine Learning Pipeline Tools
• Machine Learning Pipeline Implementation
• Iterative Machine Learning Model
• Exercise: Build Machine Learning Models & Pipelines

Model Management: Building & Deploying Machine Learning Models in Production

Course: 56 Minutes

• Course Overview
• Hyperparameter Tuning
• Hyperparameter Tuning with Grid Search
• Reproducing Study
• Machine Learning Metrics
• Machine Learning Model Versioning
• Machine Learning Model Versioning with Git and DVC
• ModelDB Architecture
• Model Management Framework
• Studio.ml Setup
• Machine Learning Model Creation
• Machine Learning Model in Production
• Deploying Machine Learning Model in Production
• Exercise: Hyperparameter Tuning and Model Versioning

Bayesian Methods: Bayesian Concepts & Core Components

Course: 1 Hour, 1 Minute

• Course Overview
• Bayesian Probability and Statistical Inference
• Bayes' Theorem in Machine Learning
• Frequentist and Subjective Probability
• Probability Distribution
• Ingredients of Bayesian Statistics
• Bayesian Methods
• Bayesian Concepts in ML Modeling
• Prior Knowledge Distribution
• Bayesian Analysis Approach
• Exercise: Bayesian Statistics and Analysis

Bayesian Methods: Implementing Bayesian Model and Computation with PyMC

Course: 48 Minutes

• Course Overview
• Bayesian Learning
• Bayesian Model Types
• Probabilistic Programming
• Modeling with PyMC
• Bayesian Data Analysis Process
• Bayesian Data Analysis with PyMC
• Bayesian Computation Methods
• Markov Chain Simulation
• Implementing Markov Chain Simulation
• Finding Posterior Modes
• Exercise: Bayesian Modeling with PyMC

Bayesian Methods: Advanced Bayesian Computation Model

Course: 52 Minutes

• Course Overview
• Bayesian Model and Linear Regression
• Hierarchical Linear Model
• Probability Model
• Building Probability Models
• Non-Linear Model
• Gaussian Process
• Mixture Model
• Dirichlet Process Model
• Bayesian Modeling with PyMC
• Exercise: Implement Bayesian models

Reinforcement Learning: Essentials

Course: 30 Minutes

• Course Overview
• Reinforcement Learning Basics
• Reinforcement Learning and Machine Learning
• Reinforcement Learning Flow
• State Change and Transition Process
• Rewards and Reinforcement Learning
• Agents in Reinforcement Learning
• Types of Reinforcement Learning Environment
• OpenAI
• Exercise: Reinforcement Learning Elements

Reinforcement Learning: Tools & Frameworks

Course: 35 Minutes

• Course Overview
• Reinforcement Learning Types
• Reinforcement Learning with Keras and Python
• Markov Decision Process
• Q-Learning Concepts
• TensorFlow Installation
• Reinforcement Learning and TensorFlow
• Q-learning and Python
• Exercise: Reinforcement Learning with Python

Math for Data Science & Machine Learning

Course: 1 Hour, 2 Minutes

• Course Overview
• Work with Vectors
• Basis and Projection of Vectors
• Work with Matrices
• Matrix Multiplication
• Matrix Division
• Linear Transformations
• Gaussian Elimination
• Determinants
• Orthogonal Matrices
• Eigenvalues
• Eigenvectors
• Pseudo Inverse
• Exercise: Math for Data Science and Machine Learning

Building ML Training Sets: Introduction

Course: 1 Hour, 10 Minutes

• Course Overview
• Loading and Exploring a Dataset
• The Binarizer
• The MinMaxScaler
• The StandardScaler
• The Normalizer
• The MaxAbsScaler
• Label Encoding
• One-Hot Encoding
• Exercise: Building ML Training Sets

Building ML Training Sets: Preprocessing Datasets for Linear Regression

Course: 51 Minutes

• Course Overview
• Loading and Analyzing a Dataset
• Scaling and Encoding the Data
• Analyzing the Effects of Preprocessing
• Standardizing Continuous Data
• Exercise: Preprocessing Data for Regression

Building ML Training Sets: Preprocessing Datasets for Classification

Course: 44 Minutes

• Course Overview
• Loading and Scaling a Dataset
• Spotting Correlations in a Dataset
• Principal Component Analysis
• Normalizing a Dataset
• Exercise: Processing Data for Classification

Linear Models & Gradient Descent: Managing Linear Models

Course: 48 Minutes

• Course Overview
• Linear Model and its Classification
• Linear Modeling Approach
• Generalized Linear Model
• ANOVA and ANCOVA
• Linear Model Implementation
• Bias, Variance and Regularization
• Ensemble Techniques
• Bagging Implementation
• Implementing Boosting Algorithm
• Exercise: Linear Models and Ensemble

Linear Models & Gradient Descent: Gradient Descent and Regularization

Course: 54 Minutes

• Course Overview
• Types of Linear Regression
• Simple and Multiple Regression
• Implementing Simple Regression
• Implementing Multiple Regression
• Gradient Descent and Types
• Gradient Descent Optimization Algorithms
• Implementing Gradient Descent
• Implementing Mini Batch Gradient Descent
• Regularization Types
• Implementing L1 & L2 Regularization
• Exercise: Regression and Gradient Descent

Online Mentor• You can reach your Mentor by entering chats or submitting an email.Final Exam assessment• Estimated duration: 90 minutesPractice Labs: Machine Learning Programming with Python (estimated duration: 8 hours)• Perform ML programming tasks with Python, such as splitting data and standardizing data, and classification using nearest neighbors and ridge regression. Then, test your skills by answering assessment questions after performing principal component analysis, visualizing correlations, training a naive Bayes model and a support vector machine model. This lab provides access to several tools commonly used in ML, including:o Microsoft Excel 2016, Visual Studio Code, Anaconda, Jupyter Notebook + JupyterHub, Pandas, NumPy, SiPy, Seaborn Library, Spyder IDE

Track 2: Deep Learning Programmer

In this track of the machine learning journey, the focus is neural networks, CNNs, RNNs, and ML algorithms.Content:E-learning courses

Getting Started with Neural Networks: Biological & Artificial Neural Networks

Course: 59 Minutes

• Course Overview
• Neural Network Fundamentals
• Biological Neural Network
• Artificial Neural Network Structure
• Neural Network Architecture
• Computational Models in Neural Networks
• Neurons Interconnection
• Threshold Functions and Artificial Neural Networks
• Implementing Neural Networks
• Building Neural Network Models
• Use Cases of Artificial Neural Network
• Exercise: Implement Neural Networks

Getting Started with Neural Networks: Perceptrons & Neural Network Algorithms

Course: 45 Minutes

• Course Overview
• Perceptrons
• Single Layer Perceptron Training Model
• Multilayer Perceptrons
• Linear and Non-Linear Functions
• Implement Perceptrons with Python
• Backpropagation
• Activation Functions
• Perceptron Classifier
• Exercise: Implement Perceptrons

Building Neural Networks: Development Principles

Course: 1 Hour, 21 Minutes

• Course Overview
• Artificial Neural Network Processing Components
• Learning and Training in Artificial Neural Network
• Cluster Analysis in Artificial Neural Network
• Neural Network Building Blocks
• Perceptron to Deep Neural Network
• Model and Hyperparameter
• Classification with Neural Networks
• Deep Learning Frameworks
• Neural Network Categorization
• Neural Network Computational Model
• Exercise: ANN Training and Classification

Building Neural Networks: Artificial Neural Networks Using Frameworks

Course: 1 Hour, 55 Minutes

• Course Overview
• Neural Network Building Components8
• Evolutionary Algorithms and Gradient Descent
• Build Neural Networks
• Building Neural Networks with PyTorch
• Object Image Classification
• Learning Rates and Deep Learning Optimization
• Optimizing Speed
• Dense Network Tuning Using Hyperas
• Linear Model with Estimators
• Neural Network for Predictions
• Optimization Approach for Predictions
• Exercise: Build Neural Networks

Training Neural Networks: Implementing the Learning Process

Course: 1 Hour, 40 Minutes

• Course Overview
• Perceptrons and Neural Networks
• Perceptron Learning Algorithm
• Learning Rules in Neural Networks
• Supervised and Unsupervised Learning
• Neural Network Algorithms
• Data Preparation For Neural Networks
• ANN Training Process in Python
• Algorithms to Train Neural Networks
• Backpropagation in Python
• Classification Algorithm for Learning
• Regularization in Multilayer Perceptrons
• Exercise: Implement ANN Learning

Training Neural Networks: Advanced Learning Algorithms

Course: 1 Hour, 41 Minutes

• Course Overview
• Online and Offline Learning
• Training Patterns and Teaching Input
• Training Samples
• Baseline Overfitting and Underfitting
• L1 and L2 Regularization
• Training Neural Networks
• Pattern Association Training Algorithms
• Learning Vector Quantization
• Modified Hebbian Learning
• Hebbian Learning Rule
• Competitive Learning
• Optimizing Neural Networks
• Debugging Neural Networks
• Exercise: Implement Advanced Algorithms

Improving Neural Networks: Neural Network Performance Management

Course: 1 Hour, 57 Minutes

• Course Overview
• Iterative Machine Learning Workflow
• Hyperparameter Optimization
• Performance Management of Neural Networks
• Impact of Dataset Sizes on Neural Network Models
• Overfitting Prevention and Management
• Neural Network Problems and Solutions
• Bias and Variance
• Implementing Bias and Variance Trade Off
• Improving Performance Using Data and Algorithm
• Model Evaluation and Selection
• Exercise: Testing Models with Scikit-learn
• Privacy and Cookie PolicyTerms of Use

Improving Neural Networks: Loss Function & Optimization

Course: 1 Hour, 4 Minutes

• Course Overview
• Loss Function
• Impact of Loss Function
• Calculating Loss Function
• Causes of Optimization Problems
• Optimizer Algorithms
• Comparing Optimizer Algorithms
• Learning Rate Optimizations
• Implement Learning Rate Optimizer
• Exercise: Working with Loss Function

Improving Neural Networks: Data Scaling & Regularization

Course: 1 Hour, 38 Minutes

• Course Overview
• Optimizing Networks
• Rate Adaption Schedule Implementation with Keras
• Scaling and Scaling Methods
• Batch Normalization and Internal Covariate Shift
• Implementing Batch Normalization
• Implementing L1 Regularization
• Implementing L2 Regularization
• Implementing Gradient Descent
• Exercise: L1 Regularization and Gradient Descent

ConvNets: Introduction to Convolutional Neural Networks

Course: 1 Hour, 1 Minute

• Course Overview
• Convolutional Neural Network Use Cases
• How Convolutional Neural Network Works
• Types of Convolutional Neural Network
• Computer Vision Problems and Techniques
• Image Recognition and Classification
• Layers and Parameters of ConvNets
• Maths for Convolutional Neural Network
• Building CNN Image Classification Model
• Exercise: Working with Convolutional Neural Networks

ConvNets: Working with Convolutional Neural Networks

Course: 43 Minutes

• Course Overview
• NN Architecture and Softmax Classifier
• Working with ConvoNetJS
• Edge Detection
• Operations on Convolutions and Pooling
• Maths and Rules for Filter and Channel Detection
• Principles of Convolutional Layers
• Activation Layer and Comparing Activation Functions
• Improving Convolutional Neural Network Model
• Exercise: Edge Detection and CNN Improvement

Convolutional Neural Networks: Fundamentals

Course: 46 Minutes

• Course Overview
• Visual Signal Perception
• CNN Architecture
• Principles of CNN
• Sparse Interaction
• Shared Parameters and Spatial Extents
• Convolutional Padding and Strides
• Pooling Layers
• CNN and ReLU
• Semantic Segmentation
• Gradient Descent and its Variants
• Exercise: CNN Architecture and Principles

Convolutional Neural Networks: Implementing & Training

Course: 31 Minutes

• Course Overview
• Image Recognition
• ResNet Layers
• PyTorch Ecosystem
• Install and Configure PyTorch
• CNN Using PyTorch
• Training CNN
• Exercise: Implementing CNNs with PyTorch

Convo Nets for Visual Recognition: Filters & Feature Mapping in CNN

Course: 1 Hour, 7 Minutes

• Course Overview
• Convolutional Networks
• Convo Nets Architecture and Layers
• Filters and Their Usage
• Filters with Keras
• Feature Map
• Plotting Feature Map with Python
• Optimization Parameters
• Hyperparameters Tuning
• Tuning Hyperparameters with TensorFlow and Keras
• Pooling Layer
• Implementing Pooling Layer
• Exercise: Plotting Feature Map

Convo Nets for Visual Recognition: Computer Vision & CNN Architectures

Course: 49 Minutes

• Course Overview
• Activation Functions and Types1
• Why ReLU in Convolutional Neural Networks
• Implementing ReLU
• Computer Vision Tasks
• Developing Object Photo Classification Model
• Fully-connected Layer
• Convolutional Neural Network Training Process
• Convolutional Neural Network Architectures
• Exercise: Applying ReLU in CNN

Fundamentals of Sequence Model: Artificial Neural Network & Sequence Modeling

Course: 36 Minutes

• Course Overview
• Artificial Neural Network (ANN)
• Components of ANN
• Modeling Tools and Frameworks
• Sequence Modeling
• Recurrent Neural Network (RNN)
• Types of RNN
• Build a RNN with PyTorch and Google Colab
• Exercise: ANN and Sequence Modeling

Fundamentals of Sequence Model: Language Model & Modeling Algorithms

Course: 19 Minutes

• Course Overview
• Language Model and NLP
• Sequence Generation for NLP
• Vanishing Gradient Problem
• Gated Recurrent Unit (GRU)
• Long Short-Term Memory (LSTM) Network
• Exercise: Language Modeling

Build & Train RNNs: Neural Network Components

Course: 37 Minutes

• Course Overview
• Artificial Neural Network
• Network Topologies
• Neuron Activation Mechanism
• Learning Samples
• Supervised, Unsupervised, and Reinforcement
• Training Samples
• Training Set and Pattern Recognition
• Gradient Optimization Procedure
• Exercise: Learning and Training Samples

Build & Train RNNs: Implementing Recurrent Neural Networks

Course: 49 Minutes

• Course Overview
• Perception and Backpropagation
• Single and Multilayer Perception
• Building Recurrent Neural Network Models
• RNN with Python and TensorFlow
• LSTM with TensorFlow
• Caffe2 and Neural Network
• Implement RNN with Caffe
• Deep Learning Language Model with Keras
• Exercise: Implement RNN Using TensorFlow and Caffe

ML Algorithms: Multivariate Calculation & Algorithms

Course: 39 Minutes

• Course Overview
• Multivariate Calculus
• Function Representation
• Gradient and Derivative
• Product and Chain Rule
• Partial Differentiation
• Linear Algebra
• Gradient and Jacobian Matrix
• Taylor's Theorem and Local Minima
• Exercise: Multivariate Operations for Calculus

ML Algorithms: Machine Learning Implementation Using Calculus & Probability

Course: 31 Minutes

• Course Overview
• Probability and Machine Learning
• Chain and Bayes Rules
• Variance and Random Vectors
• Estimation Parameters
• Deep Learning and Calculus
• R and Calculus
• Calculus in Python
• Series Expansion in Python
• Exercise: Derivatives and Integrals with SymPy

Predictive Modeling: Predictive Analytics & Exploratory Data Analysis

Course: 41 Minutes

• Course Overview
• Predictive Analytics
• Analytical Base Table
• Business Problems and Predictive Modeling
• Predictive Modeling with Python
• Exploratory Data Analysis
• Dataset and Variables Types
• Missing Values and Outlier Management
• Exercise: Predictive Modeling with Python

Predictive Modeling: Implementing Predictive Models Using Visualizations

Course: 42 Minutes

• Course Overview
• Feature Selection Algorithm
• Predictive Models
• Scatter Plots
• Pearson's Correlation
• Boxplot
• Boxplot Using Python
• Crosstab Using Python
• Statistical Concepts for Predictive Models
• Tree-Based Method
• Best Practices for Predictive Modeling
• Exercise: Implement Boxplots and Scatter Plots

Online Mentor• You can reach your Mentor by entering chats or submitting an email.Final Exam assessment• Estimated duration: 90 minutesPractice Labs: Deep Learning Programming with Python (estimated duration: 8 hours)• Perform DL programming tasks with Python, such as performing series expansion and calculus, and work with TensorFlow and scikit-image. Then, test your skills by answering assessment questions after loading a data set for hierarchical clustering and k-means clustering, and train a model using random forests and gradient boosting.

Track 3: Machine Learning Engineer

In this track of the machine learning journey, the focus is predictive modeling and analytics, ml modeling, and ml architecting.Content:E-learning collections

Predictive Modelling Best Practices: Applying Predictive Analytics

Course: 1 Hour, 27 Minutes

• Course Overview
• The Predictive Modeling Process
• Statistical Concepts for Predictive Modeling
• Regression Techniques for Predictive Analytics
• Commonly Used Models for Predictive Analytics
• Survival Analysis for Customer Churn
• Market Basket Analysis
• Data Clustering Models
• Random Forests
• Probabilistic Graphical Models
• Classification Models
• Best Practices for Predictive Modeling
• Exercise: Applying Predictive Analytics Models

Planning AI Implementation

Course: 45 Minutes

• Course Overview
• Setting Expectations
• Challenges of AI
• The Importance of Training
• The Need for Data and Algorithms
• Understanding the Human Problem
• Developing Organizational Capability
• Management Challenges
• Avoiding AI Pitfalls
• Developing a Strategy
• Data Quality
• AI Needs and Tools
• Exercise: Describe AI Planning Considerations

Automation Design & Robotics

Course: 36 Minutes

• Course Overview
• Automation Overview
• Automation Targets
• Display Status
• Human-Computer Collaboration
• Human Intervention
• Software Testing Automation
• Task Runners in Software Design and Development
• DevOps and Automated Deployment
• Software Design Patterns for Robotics
• Process Automation Using Robotics
• Modern Robotics and AI Designs
• Exercise: Applying Automation and Robotics Design

ML/DL in the Enterprise: Machine Learning Modeling, Development, & Deployment

Course: 1 Hour, 5 Minutes

• Course Overview
• Challenges of Machine Learning
• Machine Learning Process Stages
• Machine Learning Development Lifecycle
• Machine Learning Workflow
• Machine Learning Training Process
• Machine Learning Platforms
• Machine Learning Data Modelling and Processing
• H2O Machine Learning Environment
• Data Source Management
• Machine Learning Pipeline
• Git Code Movement
• Exercise: Machine Learning Training Processes

ML/DL in the Enterprise: Machine Learning Infrastructure & Metamodel

Course: 54 Minutes

• Course Overview
• Infrastructure for Data and Process
• Machine Learning and Data Pipeline
• Machine Learning Models
• Machine Learning Visualization
• Machine Learning Frameworks and Tools
• Working with H
• Model Metadata and Governance
• Risk Mitigation
• Exercise: Build Data Pipelines and Visualization

Enterprise Services: Enterprise Machine Learning with AWS

Course: 1 Hour, 14 Minutes

• Course Overview
• Cloud and Machine Learning
• Machine Learning Workflow Comparison
• AWS Machine Learning Tools and Capabilities
• Cloud Machine Learning Implementation Comparison
• Generating Machine Learning Objects and Prediction
• Amazon Machine Learning Console
• Amazon SageMaker Architecture
• Using Amazon SageMaker
• Lex, Polly, and Transcribe
• Amazon SageMaker Neo
• Augmented Manifest in Amazon SageMaker
• Amazon SageMaker Model Tuning
• Amazon SageMaker Automatic Tuning
• Course Summary

Enterprise Services: Machine Learning Implementation on Microsoft Azure

Course: 1 Hour, 13 Minutes

• Course Overview
• Azure Machine Learning Tools and Capabilities
• Comparing Azure ML Studio and Azure ML Service
• Creating & Configuring Azure ML Service Workspace
• Building ML Pipelines with Azure ML Service
• Working with Azure ML Studio
• Using Azure ML Service Visual Interface
• Working with Azure Open Datasets
• Azure MLOps
• Azure ML R Notebooks
• Pipelines with Azure Data Lake and Azure ML
• CI/CD for Machine Learning with Azure Pipeline
• Using Microsoft DevLabs Extension
• Course Summary

Enterprise Services: Machine Learning Implementation on Google Cloud Platform

Course: 1 Hour, 2 Minutes

• Course Overview
• GCP Machine Learning Tools and Capabilities
• Google Cloud Platform ML Capabilities
• Training and Job Execution with GCloud and Console
• BigQuery and BigQuery ML Features
• Implementing Models with BigQuery ML
• ML Workflow Challenges and Serverless Approach
• ML Implementation with Cloud Datalab
• Google AI Platform Features and Components
• Google Cloud AutoML Features
• Managing Dataset Using AutoML Tables
• Training Models and Predicting with AutoML Tables
• Google Cloud AutoML Natural Language
• Course Summary

Architecting Balance: Designing Hybrid Cloud Solutions

Course: 57 Minutes

• Course Overview
• Cloud Features and Deployment Models
• Comparative Analysis of On-prem and Cloud Models
• Factors Influencing On-premise & Cloud Architecture
• Hybrid vs. Private vs. Public Cloud
• Hybrid Cloud Need Assessment
• Hybrid Cloud Strategy and Architecture
• Hybrid Cloud Benefits
• Challenges of Implementing Hybrid Cloud
• Application Deployment Strategy
• Setting up Hybrid Cloud Architecture
• Exercise: Benefits of Hybrid Cloud

Enterprise Architecture: Architectural Principles & Patterns

Course: 1 Hour, 35 Minutes

• Course Overview
• Software Architecture Concepts
• Software Architecture Principles
• Architectural Models and Views
• Software Architecture Styles
• Principles of Developing Enterprise Architecture
• Architectural Principles for Data and Technology
• SOA Principles and the Maturity Model
• Serverless Architecture
• Backend-as-a-Service
• Evolutionary Architecture
• Documenting Architecture
• Project Team and Collaboration
• Consumer-Driven Contracts
• Dimensions of Architecture to Maximize Benefit
• Software Architecture Actions
• Architectural Patterns and Styles
• Course Summary

Enterprise Architecture: Design Architecture for Machine Learning Applications

Course: 1 Hour

• Course Overview
• Architecture for ML in Enterprises
• Software Architecture to Model ML Apps in Production
• Model Machine Learning Apps
• ML Reference Architecture and Building Blocks
• Evolvable Architectures and Migration
• Pitfalls of Evolutionary Architecture and Antipatterns
• Setting Up ML Solutions
• Fitness Function and Categories
• Architecture for Refinement and Production Readiness
• Course Summary

Architecting Balance: Hybrid Cloud Implementation with AWS & Azure

Course: 1 Hour, 8 Minutes

• Course Overview
• Use Cases of AWS Hybrid Cloud
• AWS Services for Hybrid Cloud Implementation
• Cloudbursting Application Hosting Model
• AWS Services for Resource and Deployment Management
• Hybrid Data Lake Implementation
• Principles and Best Practices of AWS Hybrid
• Azure Components for Hybrid Solutions
• Azure Hybrid Services
• Azure Stack
• Azure Tooling and DevOps for Hybrid Cloud
• Azure Stack Implementation
• Exercise: Implement Hybrid Cloud with Azure

Refactoring ML/DL Algorithms: Techniques & Principles

Course: 1 Hour, 6 Minutes

• Course Overview
• Role of Refactoring
• Technical Debts
• Refactoring Techniques
• PyCharm for Refactoring
• Code Analysis and Refactoring
• Design Principles
• Refactoring Principles and Challenges
• Principles of Good Code
• Refactoring Python Code
• Code Optimization
• Using Rope to Refactor
• Anti-patterns in Code
• Exercise: Refactoring Techniques

Refactoring ML/DL Algorithms: Refactor Machine Learning Algorithms

Course: 59 Minutes

• Course Overview
• Machine Learning Types
• Machine Learning Algorithm Design
• Impact of Refactoring on Machine Learning
• Algorithm Design
• Machine Learning Algorithm Comparison
• Refactor Machine Learning Code
• Managing Technical Debt in Machine Learning
• SonarQube and Code Coverage
• Automatic Clone Refactoring
• Exercise: Refactoring Machine Learning Code

Online Mentor• You can reach your Mentor by entering chats or submitting an email.Final Exam assessment• Estimated duration: 90 minutesPractice Labs: Architecting ML/DL Apps with Python (estimated duration: 8 hours)• Perform architecting tasks such as binning data, imputing values, performing cross validation, and evaluating a classification model. Then, test your skills by answering assessment questions after validating a model, tuning parameters, refactoring a machine learning model, and saving and loading models using Python.

Track 4: Machine Learning Architect

In this track of the machine learning journey, the focus is applied predictive modeling, CNNs and RNNs, and ML algorithms.Content:E-learning collections

Applied Predictive Modeling

Course: 1 Hour, 8 Minutes

• Course Overview
• Overview of Predictive Modeling
• Exploratory Data Analysis
• Overview of Regression Methods
• Linear Regression in Python
• Logistic Regression in Python
• Overview of Clustering Methods
• Hierarchical Clustering in Python
• K-Means Clustering in Python
• Overview of Decision Trees and Random Forests
• Decision Trees in Python
• Random Forests in Python
• Exercise: Apply Predictive Models

Implementing Deep Learning: Practical Deep Learning Using Frameworks & Tools

Course: 1 Hour

• Course Overview
• Comparing DL and ML
• ML/DL Workflow
• Deep Learning Network Components
• DL/ML Frameworks
• Recurrent CNN with Caffe
• Autoencoders and PyTorch
• Deep Neural Network Implementation
• Platform and Framework Comparison
• Selecting the Right ML/DL Frameworks
• Challenges of Debugging Deep Learning Networks
• Exercise: Using DL Frameworks and Tools

Implementing Deep Learning: Optimized Deep Learning Applications

Course: 43 Minutes

• Course Overview
• Computational Graph and Deep Learning
• Accelerating Architectures
• GPU Interfaces
• TFX and Pipeline Components for ML Pipelines
• Setting up TFX
• Build TFX Pipeline
• Using TFMA
• Practical Consideration for DL Build and Train
• Deep Learning Parameters
• Exercise: Optimizing Deep Learning Applications

Applied Deep Learning: Unsupervised Data

Course: 1 Hour, 28 Minutes

• Course Overview
• Deep Learning to Model NLP and Audio Analysis
• Recurrent Neural Network Architectures
• Unsupervised Learning Challenges in Deep Learning
• Generative and Discriminative Classifiers
• Types of Generative Models
• PixelCNN Setup
• Differences between MLP, CNN, and RNN
• ResNet for Computer Vision
• Encoders and Autoencoders
• Exercise: RNN and ResNet

Applied Deep Learning: Generative Adversarial Networks and Q-Learning

Course: 45 Minutes

• Course Overview
• Implement Autoencoder Using Keras
• Implementing Generative Adversarial Networks
• Building GAN Model Using Python and Keras
• Generative Adversarial Network Challenges
• Deep Reinforcement Learning
• Deep RL and Deep Learning Comparison
• Generative Adversarial Network Variations
• Deep Q-Learning
• Deep Q-Learning in Python
• Exercise: Implementing GAN and Deep Q-Learning

Advanced Reinforcement Learning: Principles

Course: 1 Hour, 13 Minutes

• Course Overview
• Reinforcement Learning Concepts
• Comparing Reinforcement and Machine Learning
• Reinforcement Learning Use Cases
• Reinforcement Learning Terms and Workflow
• Reinforcement Learning Implementation Approaches
• Reinforcement Learning Algorithms
• Markov Decision Process and Its Variants
• Markov Reward Process and Value Functions
• Markov Decision Process Toolbox Capabilities
• Exercise: Reinforcement Learning and MDP Toolbox

Advanced Reinforcement Learning: Implementation

Course: 1 Hour, 35 Minutes

• Course Overview
• Installing the Markov Decision Process Toolbox
• Rewards and Discounts
• Multi-Armed Bandit Problem
• Dynamic Programming and Bellman Equation
• Reinforcement Learning Agent and Its Components
• Reinforcement Learning with OpenAI Gym and Keras
• Reinforcement Learning Taxonomy by OpenAI
• Deep Q-Learning Implementation
• Training DNN Using Reinforcement Learning
• Exercise: Implementing Deep Q-Learning

ML/DL Best Practices: Machine Learning Workflow Best Practices

Course: 53 Minutes

• Course Overview
• Installing the Markov Decision Process Toolbox
• Rewards and Discounts
• Multi-Armed Bandit Problem
• Dynamic Programming and Bellman Equation
• Reinforcement Learning Agent and Its Components
• Reinforcement Learning with OpenAI Gym and Keras
• Reinforcement Learning Taxonomy by OpenAI
• Deep Q-Learning Implementation
• Training DNN Using Reinforcement Learning
• Exercise: Implementing Deep Q-Learning

ML/DL Best Practices: Building Pipelines with Applied Rules

Course: 1 Hour, 4 Minutes

• Course Overview
• Troubleshooting Deep Learning and Using Checklists
• ML Technical Challenges and Best Practices
• Case Study to Analyze Impacts of Best Practices
• Deployment Challenges and Patterns
• Case Study of Deployment Approaches
• Architecting and Building ML Pipelines
• Rules for Building Machine Learning Pipelines
• Feature Engineering Rules
• Training-Serving Skew
• Rules for Managing Optimization Refinement
• ML Project Checklists for Project Managers
• Course Summary

Research Topics in ML and DL

Course: 42 Minutes

• Course Overview
• Prevent Neural Networks from Overfitting
• Multi-Label Learning Algorithms
• Deep Residual Learning for Image Recognition
• Transferable Features in Deep Neural Networks
• Large-Scale Video Classification
• Common Objects in Context
• Generative Adversarial Nets
• Scalable Nearest Neighbor Algorithms
• Face Alignment with Ensemble of Regression Trees
• Learning Deep Features for Scene Recognition
• Extreme Learning Machine (ELM)
• Exercise: Recognize Research Topics in ML and DL

Deep Learning with Keras

Course: 1 Hour, 56 Minutes

• Course Overview
• Neural Networks
• Introduction to Keras
• Keras Backend
• Set up Keras
• Model Types in Keras
• Keras Layers
• Regression Classification
• Image Classification
• Keras Metrics
• Jupyter Notebooks
• Dataset for Neural Network
• Explore Your Dataset
• Data Preparation
• Compiling the Model
• Training and Testing Neural Networks
• Evaluate the Model
• Making Predictions
• Exercise: Using a Neural Network

Online Mentor• You can reach your Mentor by entering chats or submitting an email.Final Exam assessment• Estimated duration: 90 minutesPractice Labs: Architecting Advanced ML/DL Apps with Python (estimated duration: 8 hours)• Perform advanced ML/DL app architecture tasks using Python, such as loading a data set to train a simple multilayer perceptron (MLP), a Convolutional Neural Network (CNN) and an LSTM model. Then, test your skills by answering assessment questions after performing image and text classification using CNN.