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
- Statistical learning versus machine learning
- Iterative processes and evaluation protocols
- Bias-Variance trade-off considerations
- Supervised versus Unsupervised Learning paradigms
- Problem domains addressable via Machine Learning
- Train-Validation-Test split: ML workflow to prevent overfitting
- Standard Machine Learning workflow
- Classification of Machine learning algorithms
- Selecting an appropriate algorithm for specific problem contexts
Algorithm Evaluation
-
Assessment of numerical predictions
- Accuracy metrics: ME, MSE, RMSE, MAPE
- Stability of parameters and predictions
-
Assessment of classification algorithms
- Accuracy metrics and associated limitations
- Utilization of the confusion matrix
- Management of unbalanced class distributions
-
Visualization of model performance
- Profit curve analysis
- Lift curve analysis
- Model selection strategies
- Model tuning: grid search methodologies
Data preparation for Modelling
- Data import and storage protocols
- Data understanding – initial explorations
- Data manipulation using the pandas library
- Data transformations: Data wrangling
- Exploratory Data Analysis (EDA)
- Missing observations: detection and remediation
- Outliers: detection and mitigation strategies
- Standardization, normalization, and binarization
- Recoding of 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
- Overview of Deep Learning applications
Overview of Neural Networks
- Definition of Neural Networks
- Neural Networks versus Regression Models
- Mathematical foundations and learning mechanisms
- Constructing an Artificial Neural Network
- Analysis of Neural Nodes and Connections
- Interaction of Neurons, Layers, and Input/Output Data
- Single Layer Perceptrons
- Distinctions between Supervised and Unsupervised Learning
- Forward Propagation and Back Propagation mechanisms
Building Simple Deep Learning Models with Keras
- Initialization of a Keras Model
- Data comprehension and preparation
- Specification of the Deep Learning Model architecture
- Model compilation process
- Model fitting procedures
- Processing of Classification Data
- Implementation of Classification Models
- Deployment and utilization of Models
Working with TensorFlow for Deep Learning
-
Data Preparation
- Data acquisition
- Preparation of Training Data
- Preparation of Test Data
- Input scaling techniques
- Utilization of Placeholders and Variables
- Definition of the Network Architecture
- Application of the Cost Function
- Application of the Optimizer
- Fitting the Neural Network
-
Graph Construction
- Inference
- Loss calculation
- Training loop
-
Model Training
- Graph structure
- Session management
- Train Loop implementation
-
Model Evaluation
- Construction of the Eval Graph
- Evaluation via Eval Output
- Scaling Model Training
- Model Visualization and Evaluation using TensorBoard
Application of Deep Learning in Anomaly Detection
-
Autoencoder
- Encoder-Decoder Architecture
- Reconstruction loss metrics
-
Variational Autoencoder
- Variational inference methods
-
Generative Adversarial Network
- Generator-Discriminator architecture
- Application of GAN for AN detection
Ensemble Frameworks
- Aggregation of results from diverse methods
- Bootstrap Aggregating (Bagging)
- Averaging of outlier scores
Requirements
- Proficiency in Python programming
Target Audience
- Developers
- Data scientists
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
