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.
- Iteration and evaluation processes.
- The Bias-Variance trade-off.
- Supervised versus Unsupervised Learning.
- Types of problems solved using Machine Learning.
- Train, Validation, Test split – ML workflow to prevent overfitting.
- The Machine learning workflow.
- Machine learning algorithms.
- Selecting the appropriate algorithm for a given problem.
Algorithm Evaluation
-
Evaluating numerical predictions
- Measures of accuracy: MAE, MSE, RMSE, MAPE.
- Stability of parameters and predictions.
-
Evaluating classification algorithms
- Accuracy and its limitations.
- The confusion matrix.
- The issue of imbalanced classes.
-
Visualizing model performance
- Profit curve.
- ROC curve.
- Lift curve.
- Model selection strategies.
- Model tuning – grid search strategies.
Data Preparation for Modelling
- Data import and storage mechanisms.
- Understanding the data – initial explorations.
- Data manipulations using the pandas library.
- Data transformations – Data wrangling.
- Exploratory data analysis.
- Missing observations – detection and remediation.
- Outliers – detection and handling strategies.
- Standardization, normalization, and binarization.
- Recoding qualitative data.
Machine Learning Algorithms for Outlier Detection
-
Supervised algorithms
- K-Nearest Neighbors (KNN).
- Ensemble Gradient Boosting.
- Support Vector Machines (SVM).
-
Unsupervised algorithms
- Distance-based methods.
- Density-based methods.
- Probabilistic methods.
- Model-based methods.
Understanding Deep Learning
- Overview of the basic concepts of deep learning.
- Differentiating between Machine Learning and Deep Learning.
- Overview of applications for deep learning.
Overview of Neural Networks
- Definition and nature of Neural Networks.
- Neural Networks versus Regression Models.
- Understanding the 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 Backpropagation.
Building Simple Deep Learning Models with Keras
- Creating a Keras Model.
- Understanding your data.
- Specifying your Deep Learning Model.
- Compiling your Model.
- Fitting your Model.
- Working with your Classification data.
- Working with Classification Models.
- Using 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.
- Specifying the Network Architecture.
- Using the Cost Function.
- Using the Optimizer.
- Using Initializers.
- Fitting the Neural Network.
-
Building the Graph
- Inference.
- Loss calculation.
- Training process.
-
Training the Model
- The Graph structure.
- The Session management.
- Training Loop.
-
Evaluating the Model
- Building the Evaluation 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 Autoencoder
- Variational inference.
-
Generative Adversarial Network (GAN)
- Generator-Discriminator architecture.
- Approaches to Anomaly Detection (AD) using GANs.
Ensemble Frameworks
- Combining results from different methods.
- Bootstrap Aggregating (Bagging).
- Averaging outlier scores.
Requirements
- Prior experience with Python programming.
- Basic familiarity with statistical and mathematical concepts.
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
