Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Introduction to Applied Machine Learning
<\/h3>
-
Statistical learning versus Machine learning
<\/li>
-
Iteration and evaluation
<\/li>
-
Bias-Variance trade-off
<\/li>
-
Supervised versus Unsupervised Learning
<\/li>
-
Problems solved with Machine Learning
<\/li>
-
Train Validation Test – ML workflow to prevent overfitting
<\/li>
-
Workflow of Machine Learning
<\/li>
-
Machine learning algorithms
<\/li>
-
Selecting the appropriate algorithm for the problem
<\/li>
<\/ul>
Algorithm Evaluation
<\/h3>
-
Evaluating numerical predictions
-
Accuracy measures: ME, MSE, RMSE, MAPE
<\/li>
-
Parameter and prediction stability
<\/li>
<\/ul>
<\/li>
-
Evaluating classification algorithms
-
Accuracy and its limitations
<\/li>
-
The confusion matrix
<\/li>
-
Issues with unbalanced classes
<\/li>
<\/ul>
<\/li>
-
Visualizing model performance
-
Profit curve
<\/li>
-
ROC curve
<\/li>
-
Lift curve
<\/li>
<\/ul>
<\/li>
-
Model selection
<\/li>
-
Model tuning – grid search strategies
<\/li>
<\/ul>
Data preparation for Modelling
<\/h3>
-
Data import and storage
<\/li>
-
Understanding the data – basic explorations
<\/li>
-
Data manipulations with pandas library
<\/li>
-
Data transformations – Data wrangling
<\/li>
-
Exploratory analysis
<\/li>
-
Missing observations – detection and solutions
<\/li>
-
Outliers – detection and strategies
<\/li>
-
Standardization, normalization, binarization
<\/li>
-
Recoding qualitative data
<\/li>
<\/ul>
Machine learning algorithms for Outlier detection
<\/h3>
-
Supervised algorithms
-
KNN
<\/li>
-
Ensemble Gradient Boosting
<\/li>
-
SVM
<\/li>
<\/ul>
<\/li>
-
Unsupervised algorithms
-
Distance-based
<\/li>
-
Density based methods
<\/li>
-
Probabilistic methods
<\/li>
-
Model based methods
<\/li>
<\/ul>
<\/li>
<\/ul>
Understanding Deep Learning
<\/h3>
-
Overview of the Basic Concepts of Deep Learning
<\/li>
-
Differentiating Between Machine Learning and Deep Learning
<\/li>
-
Overview of Applications for Deep Learning
<\/li>
<\/ul>
Overview of Neural Networks
<\/h3>
-
What are Neural Networks
<\/li>
-
Neural Networks versus Regression Models
<\/li>
-
Understanding Mathematical Foundations and Learning Mechanisms
<\/li>
-
Constructing an Artificial Neural Network
<\/li>
-
Understanding Neural Nodes and Connections
<\/li>
-
Working with Neurons, Layers, and Input and Output Data
<\/li>
-
Understanding Single Layer Perceptrons
<\/li>
-
Differences Between Supervised and Unsupervised Learning
<\/li>
-
Learning Feedforward and Feedback Neural Networks
<\/li>
-
Understanding Forward Propagation and Back Propagation
<\/li>
<\/ul>
Building Simple Deep Learning Models with Keras
<\/h3>
-
Creating a Keras Model
<\/li>
-
Understanding Your Data
<\/li>
-
Specifying Your Deep Learning Model
<\/li>
-
Compiling Your Model
<\/li>
-
Fitting Your Model
<\/li>
-
Working with Your Classification Data
<\/li>
-
Working with Classification Models
<\/li>
-
Using Your Models
<\/li>
<\/ul>
Working with TensorFlow for Deep Learning
<\/h3>
-
Preparing the Data
-
Downloading the Data
<\/li>
-
Preparing Training Data
<\/li>
-
Preparing Test Data
<\/li>
-
Scaling Inputs
<\/li>
-
Using Placeholders and Variables
<\/li>
<\/ul>
<\/li>
-
Specifying the Network Architecture
<\/li>
-
Using the Cost Function
<\/li>
-
Using the Optimizer
<\/li>
-
Using Initializers
<\/li>
-
Fitting the Neural Network
<\/li>
-
Building the Graph
-
Inference
<\/li>
-
Loss
<\/li>
-
Training
<\/li>
<\/ul>
<\/li>
-
Training the Model
-
The Graph
<\/li>
-
The Session
<\/li>
-
Train Loop
<\/li>
<\/ul>
<\/li>
-
Evaluating the Model
-
Building the Eval Graph
<\/li>
-
Evaluating with Eval Output
<\/li>
<\/ul>
<\/li>
-
Training Models at Scale
<\/li>
-
Visualizing and Evaluating Models with TensorBoard
<\/li>
<\/ul>
Application of Deep Learning in Anomaly Detection
<\/h3>
-
Autoencoder
-
Encoder - Decoder Architecture
<\/li>
-
Reconstruction loss
<\/li>
<\/ul>
<\/li>
-
Variational Autoencoder
-
Variational inference
<\/li>
<\/ul>
<\/li>
-
Generative Adversarial Network
-
Generator – Discriminator architecture
<\/li>
-
Approaches to AN using GAN
<\/li>
<\/ul>
<\/li>
<\/ul>
Ensemble Frameworks
<\/h3>
-
Combining results from different methods
<\/li>
-
Bootstrap Aggregating
<\/li>
-
Averaging outlier score
<\/li>
<\/ul>
Algorithm Evaluation
<\/h3>
-
Evaluating numerical predictions
-
Accuracy measures: ME, MSE, RMSE, MAPE
<\/li>
-
Parameter and prediction stability
<\/li>
<\/ul>
<\/li>
-
Evaluating classification algorithms
-
Accuracy and its limitations
<\/li>
-
The confusion matrix
<\/li>
-
Issues with unbalanced classes
<\/li>
<\/ul>
<\/li>
-
Visualizing model performance
-
Profit curve
<\/li>
-
ROC curve
<\/li>
-
Lift curve
<\/li>
<\/ul>
<\/li>
-
Model selection
<\/li>
-
Model tuning – grid search strategies
<\/li>
<\/ul>
Data preparation for Modelling
<\/h3>
-
Data import and storage
<\/li>
-
Understanding the data – basic explorations
<\/li>
-
Data manipulations with pandas library
<\/li>
-
Data transformations – Data wrangling
<\/li>
-
Exploratory analysis
<\/li>
-
Missing observations – detection and solutions
<\/li>
-
Outliers – detection and strategies
<\/li>
-
Standardization, normalization, binarization
<\/li>
-
Recoding qualitative data
<\/li>
<\/ul>
Machine learning algorithms for Outlier detection
<\/h3>
-
Supervised algorithms
-
KNN
<\/li>
-
Ensemble Gradient Boosting
<\/li>
-
SVM
<\/li>
<\/ul>
<\/li>
-
Unsupervised algorithms
-
Distance-based
<\/li>
-
Density based methods
<\/li>
-
Probabilistic methods
<\/li>
-
Model based methods
<\/li>
<\/ul>
<\/li>
<\/ul>
Understanding Deep Learning
<\/h3>
-
Overview of the Basic Concepts of Deep Learning
<\/li>
-
Differentiating Between Machine Learning and Deep Learning
<\/li>
-
Overview of Applications for Deep Learning
<\/li>
<\/ul>
Overview of Neural Networks
<\/h3>
-
What are Neural Networks
<\/li>
-
Neural Networks versus Regression Models
<\/li>
-
Understanding Mathematical Foundations and Learning Mechanisms
<\/li>
-
Constructing an Artificial Neural Network
<\/li>
-
Understanding Neural Nodes and Connections
<\/li>
-
Working with Neurons, Layers, and Input and Output Data
<\/li>
-
Understanding Single Layer Perceptrons
<\/li>
-
Differences Between Supervised and Unsupervised Learning
<\/li>
-
Learning Feedforward and Feedback Neural Networks
<\/li>
-
Understanding Forward Propagation and Back Propagation
<\/li>
<\/ul>
Building Simple Deep Learning Models with Keras
<\/h3>
-
Creating a Keras Model
<\/li>
-
Understanding Your Data
<\/li>
-
Specifying Your Deep Learning Model
<\/li>
-
Compiling Your Model
<\/li>
-
Fitting Your Model
<\/li>
-
Working with Your Classification Data
<\/li>
-
Working with Classification Models
<\/li>
-
Using Your Models
<\/li>
<\/ul>
Working with TensorFlow for Deep Learning
<\/h3>
-
Preparing the Data
-
Downloading the Data
<\/li>
-
Preparing Training Data
<\/li>
-
Preparing Test Data
<\/li>
-
Scaling Inputs
<\/li>
-
Using Placeholders and Variables
<\/li>
<\/ul>
<\/li>
-
Specifying the Network Architecture
<\/li>
-
Using the Cost Function
<\/li>
-
Using the Optimizer
<\/li>
-
Using Initializers
<\/li>
-
Fitting the Neural Network
<\/li>
-
Building the Graph
-
Inference
<\/li>
-
Loss
<\/li>
-
Training
<\/li>
<\/ul>
<\/li>
-
Training the Model
-
The Graph
<\/li>
-
The Session
<\/li>
-
Train Loop
<\/li>
<\/ul>
<\/li>
-
Evaluating the Model
-
Building the Eval Graph
<\/li>
-
Evaluating with Eval Output
<\/li>
<\/ul>
<\/li>
-
Training Models at Scale
<\/li>
-
Visualizing and Evaluating Models with TensorBoard
<\/li>
<\/ul>
Application of Deep Learning in Anomaly Detection
<\/h3>
-
Autoencoder
-
Encoder - Decoder Architecture
<\/li>
-
Reconstruction loss
<\/li>
<\/ul>
<\/li>
-
Variational Autoencoder
-
Variational inference
<\/li>
<\/ul>
<\/li>
-
Generative Adversarial Network
-
Generator – Discriminator architecture
<\/li>
-
Approaches to AN using GAN
<\/li>
<\/ul>
<\/li>
<\/ul>
Ensemble Frameworks
<\/h3>
-
Combining results from different methods
<\/li>
-
Bootstrap Aggregating
<\/li>
-
Averaging outlier score
<\/li>
<\/ul>
- Accuracy measures: ME, MSE, RMSE, MAPE <\/li>
- Parameter and prediction stability <\/li> <\/ul> <\/li>
-
Evaluating classification algorithms
- Accuracy and its limitations <\/li>
- The confusion matrix <\/li>
- Issues with unbalanced classes <\/li> <\/ul> <\/li>
-
Visualizing model performance
- Profit curve <\/li>
- ROC curve <\/li>
- Lift curve <\/li> <\/ul> <\/li>
- Model selection <\/li>
-
Model tuning – grid search strategies
<\/li>
<\/ul>
Data preparation for Modelling <\/h3>
- Data import and storage <\/li>
- Understanding the data – basic explorations <\/li>
- Data manipulations with pandas library <\/li>
- Data transformations – Data wrangling <\/li>
- Exploratory analysis <\/li>
- Missing observations – detection and solutions <\/li>
- Outliers – detection and strategies <\/li>
- Standardization, normalization, binarization <\/li>
-
Recoding qualitative data
<\/li>
<\/ul>
Machine learning algorithms for Outlier detection <\/h3>
-
Supervised algorithms
- KNN <\/li>
- Ensemble Gradient Boosting <\/li>
- SVM <\/li> <\/ul> <\/li>
-
Unsupervised algorithms
- Distance-based <\/li>
- Density based methods <\/li>
- Probabilistic methods <\/li>
-
Model based methods
<\/li>
<\/ul>
<\/li>
<\/ul>
Understanding Deep Learning <\/h3>
- Overview of the Basic Concepts of Deep Learning <\/li>
- Differentiating Between Machine Learning and Deep Learning <\/li>
-
Overview of Applications for Deep Learning
<\/li>
<\/ul>
Overview of Neural Networks <\/h3>
- What are Neural Networks <\/li>
- Neural Networks versus Regression Models <\/li>
- Understanding Mathematical Foundations and Learning Mechanisms <\/li>
- Constructing an Artificial Neural Network <\/li>
- Understanding Neural Nodes and Connections <\/li>
- Working with Neurons, Layers, and Input and Output Data <\/li>
- Understanding Single Layer Perceptrons <\/li>
- Differences Between Supervised and Unsupervised Learning <\/li>
- Learning Feedforward and Feedback Neural Networks <\/li>
-
Understanding Forward Propagation and Back Propagation
<\/li>
<\/ul>
Building Simple Deep Learning Models with Keras <\/h3>
- Creating a Keras Model <\/li>
- Understanding Your Data <\/li>
- Specifying Your Deep Learning Model <\/li>
- Compiling Your Model <\/li>
- Fitting Your Model <\/li>
- Working with Your Classification Data <\/li>
- Working with Classification Models <\/li>
-
Using Your Models
<\/li>
<\/ul>
Working with TensorFlow for Deep Learning <\/h3>
-
Preparing the Data
- Downloading the Data <\/li>
- Preparing Training Data <\/li>
- Preparing Test Data <\/li>
- Scaling Inputs <\/li>
- Using Placeholders and Variables <\/li> <\/ul> <\/li>
- Specifying the Network Architecture <\/li>
- Using the Cost Function <\/li>
- Using the Optimizer <\/li>
- Using Initializers <\/li>
- Fitting the Neural Network <\/li>
-
Building the Graph
- Inference <\/li>
- Loss <\/li>
- Training <\/li> <\/ul> <\/li>
-
Training the Model
- The Graph <\/li>
- The Session <\/li>
- Train Loop <\/li> <\/ul> <\/li>
-
Evaluating the Model
- Building the Eval Graph <\/li>
- Evaluating with Eval Output <\/li> <\/ul> <\/li>
- Training Models at Scale <\/li>
-
Visualizing and Evaluating Models with TensorBoard
<\/li>
<\/ul>
Application of Deep Learning in Anomaly Detection <\/h3>
-
Autoencoder
- Encoder - Decoder Architecture <\/li>
- Reconstruction loss <\/li> <\/ul> <\/li>
-
Variational Autoencoder
- Variational inference <\/li> <\/ul> <\/li>
-
Generative Adversarial Network
- Generator – Discriminator architecture <\/li>
-
Approaches to AN using GAN
<\/li>
<\/ul>
<\/li>
<\/ul>
Ensemble Frameworks <\/h3>
- Combining results from different methods <\/li>
- Bootstrap Aggregating <\/li>
- Averaging outlier score <\/li> <\/ul>
-
Autoencoder
-
Preparing the Data
-
Supervised algorithms
Requirements
- Experience with Python programming <\/li>
-
Basic familiarity with statistics and mathematical concepts
<\/li>
<\/ul>
Target Audience<\/strong> <\/p>
- Developers <\/li>
- Data scientists <\/li> <\/ul>
28 Hours
Testimonials (5)
The training provided an interesting overview of deep learning models and related methods. The topic was quite new to me, but now I feel like I actually have an idea of what AI and ML can involve, what these terms consist of and how they can be used advantageously. In general, I liked the approach of starting with the statistical background and the basic learning models, such as linear regression, especially emphasizing the exercises in between.
Konstantin - REGNOLOGY ROMANIA S.R.L.
Course - Fundamentals of Artificial Intelligence (AI) and Machine Learning
Anna was always asking if there are questions, and always tried to make us more active by posing questions, which made all of us really involved into the training.
Enes Gicevic - REGNOLOGY ROMANIA S.R.L.
Course - Fundamentals of Artificial Intelligence (AI) and Machine Learning
I liked the way how it is blended with the practices.
Bertan - REGNOLOGY ROMANIA S.R.L.
Course - Fundamentals of Artificial Intelligence (AI) and Machine Learning
The extensive experience / knowledge of the trainer
Ovidiu - REGNOLOGY ROMANIA S.R.L.
Course - Fundamentals of Artificial Intelligence (AI) and Machine Learning
the VM is a nice idea
