Course Outline
Introduction to Applied Machine Learning
- Statistical learning versus Machine learning
- Iterative processes and evaluation
- The Bias-Variance trade-off
- Supervised versus Unsupervised Learning
- Problems addressed through Machine Learning
- Train, Validation, and Test sets – ML workflow to prevent overfitting
- The Machine Learning Workflow
- Overview of machine learning algorithms
- Selecting the appropriate algorithm for specific problems
Algorithm Evaluation
-
Assessing numerical predictions
- Accuracy metrics: ME, MSE, RMSE, MAPE
- Stability of parameters and predictions
-
Assessing classification algorithms
- Accuracy and its limitations
- Interpreting the confusion matrix
- Addressing the issue of unbalanced classes
-
Visualizing model performance
- Profit curve
- ROC curve
- Lift curve
- Model selection techniques
- Model tuning – grid search strategies
Data Preparation for Modelling
- Data import and storage management
- Understanding the data – initial explorations
- Data manipulation using the pandas library
- Data transformations – Data wrangling
- Conducting exploratory analysis
- Handling missing observations – detection and remedies
- Outliers – identification and handling strategies
- Standardization, normalization, and binarization
- Recoding qualitative data
Machine Learning Algorithms for Outlier Detection
-
Supervised algorithms
- KNN
- Ensemble Gradient Boosting
- SVM
-
Unsupervised algorithms
- Distance-based methods
- Density-based methods
- Probabilistic methods
- Model-based methods
Understanding Deep Learning
- Overview of fundamental Deep Learning concepts
- Distinguishing between Machine Learning and Deep Learning
- Overview of Deep Learning applications
Overview of Neural Networks
- Definition of Neural Networks
- Neural Networks compared to Regression Models
- Grasping mathematical foundations and learning mechanisms
- Constructing an Artificial Neural Network
- Understanding Neural Nodes and Connections
- Working with Neurons, Layers, and Input/Output Data
- Understanding Single Layer Perceptrons
- Differences between Supervised and Unsupervised Learning
- Learning Feedforward and Feedback Neural Networks
- Understanding Forward Propagation and Back Propagation
Building Simple Deep Learning Models with Keras
- Creating a Keras Model
- Analyzing the Data
- Specifying the Deep Learning Model
- Compiling the Model
- Fitting the Model
- Working with Classification Data
- Working with Classification Models
- Deploying Your Models
Working with TensorFlow for Deep Learning
-
Preparing the Data
- Downloading the Data
- Preparing Training Data
- Preparing Test Data
- Scaling Inputs
- Using Placeholders and Variables
- Defining the Network Architecture
- Utilizing the Cost Function
- Using the Optimizer
- Using Initializers
- Fitting the Neural Network
-
Building the Graph
- Inference
- Loss
- Training
-
Training the Model
- The Graph
- The Session
- Training Loop
-
Evaluating the Model
- Building the Eval Graph
- Evaluating with Eval Output
- Training Models at Scale
- Visualizing and Evaluating Models with TensorBoard
Application of Deep Learning in Anomaly Detection
-
Autoencoder
- Encoder - Decoder Architecture
- Reconstruction loss
-
Variational Autencoder
- Variational inference
-
Generative Adversarial Network
- Generator – Discriminator architecture
- Approaches to AN using GAN
Ensemble Frameworks
- Combining results from various methods
- Bootstrap Aggregating
- Averaging outlier scores
Requirements
- Proficiency in Python programming
- Basic understanding of statistics and mathematical concepts
Target Audience
- Software Developers
- Data Scientists
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