Fundamentals of

Artificial Intelligence (AI) &

Machine Learning (ML)


Machine learning represents a subset of Artificial Intelligence where machines gain the capability to learn autonomously without direct programming.

Deep learning, a specialized area within machine learning, employs algorithms inspired by the structure and function of the brain’s neural networks to interpret complex data patterns.

Python, renowned for its straightforward syntax and code legibility, is a widely-used high-level programming language.

During this interactive, live training, participants will delve into the application of deep learning in the telecommunications sector using Python, culminating in the development of a model to assess credit risk.

At the conclusion of this training, participants will:

– Grasp the key principles of deep learning.
– Explore deep learning’s role and potential within the telecom industry.
– Employ Python alongside Keras and TensorFlow to construct telecommunication-focused deep learning models.
– Develop a bespoke model for predicting customer churn with Python.


Training Approach:

– Engaging lectures complemented by in-depth discussions.
– Extensive hands-on exercises and practical application.
– Real-time coding and model development in a live-lab setup.

To tailor this course to meet your specific learning needs, please reach out to us for a personalized training arrangement.

Course Outlines

Introduction to Applied Machine Learning

  • Statistical learning vs. Machine learning
  • Iteration and evaluation
  • Bias-Variance trade-off
  • Supervised vs Unsupervised Learning
  • Problems solved with Machine Learning
  • Train Validation Test – ML workflow to avoid overfitting
  • Workflow of Machine Learning
  • Machine learning algorithms
  • Choosing appropriate algorithm to the problem

Algorithm Evaluation

  • Evaluating numerical predictions
    • Measures of accuracy: ME, MSE, RMSE, MAPE
    • Parameter and prediction stability
  • Evaluating classification algorithms
    • Accuracy and its problems
    • The confusion matrix
    • Unbalanced classes problem
  • Visualizing model performance
    • Profit curve
    • ROC curve
    • Lift curve
  • Model selection
  • Model tuning – grid search strategies

Data preparation for Modelling

  • Data import and storage
  • Understand the data – basic explorations
  • Data manipulations with pandas library
  • Data transformations – Data wrangling
  • Exploratory analysis
  • Missing observations – detection and solutions
  • Outliers – detection and strategies
  • Standarization, normalization, binarization
  • Qualitative data recoding

Machine learning algorithms for Outlier detection

  • Supervised algorithms
    • KNN
    • Ensemble Gradient Boosting
    • SVM
  • Unsupervised algorithms
    • Distance-based
    • 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

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 

Overview of Neural Networks

  • What are Neural Networks
  • Neural Networks vs Regression Models
  • Understanding Mathematical Foundations and Learning Mechanisms
  • Constructing an Artificial Neural Network
  • Understanding Neural Nodes and Connections
  • Working with Neurons, Layers, and Input and Output Data
  • Understanding Single Layer Perceptrons
  • Differences Between Supervised and Unsupervised Learning
  • Learning Feedforward and Feedback Neural Networks
  • Understanding Forward Propagation and Back Propagation

    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
      • Training
    • Training the Model
      • The Graph
      • The Session
      • Train 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 different methods
    • Bootstrap Aggregating
    • Averaging outlier score