Let us help you find the training program you are looking for.

If you can't find what you are looking for, contact us, we'll help you find it. We have over 800 training programs to choose from.

Loading Events

Python Machine Learning – 3 Day Training Session

Course Details:

  • Cost per Student:

    $ 2100

Course Objectives

  • Widely acclaimed Python machine learning course  
  • Clear and intuitive explanations take you deep into the theory and practice of Python machine learning
  • Fully updated and expanded to cover TensorFlow 2, Generative Adversarial Network models, reinforcement learning, and best practices  
  • Mastering the frameworks, models, and techniques that enable machines to ‘learn’ from data  
  • Using scikit-learn for machine learning and TensorFlow for deep learning  
  • Applying machine learning to image classification, sentiment analysis, intelligent web applications, and more  
  • Building and training neural networks, GANs, and other models  
  • Discovering best practices for evaluating and tuning models  
  • Predicting continuous target outcomes using regression analysis  
  • Digging deeper into textual and social media data using sentiment analysis  


Course breakdown / Modules:  

  1. Giving Computers the Ability to Learn from Data  
    1. Building intelligent machines to transform data into knowledge  
    2. The three different types of machine learning  
    3. Introduction to the basic terminology and notations  
    4. A roadmap for building machine learning systems  
    5. Using Python for machine learning  
  2. Training Simple Machine Learning Algorithms for Classification  
    1. Artificial neurons – a brief glimpse into the early history of machine learning  
    2. Implementing a perceptron learning algorithm in Python  
    3. Adaptive linear neurons and the convergence of learning  
  3. A Tour of Machine Learning Classifiers Using scikit-learn  
    1. Choosing a classification algorithm  
    2. First steps with scikit-learn – training a perceptron  
    3. Modeling class probabilities via logistic regression  
    4. Maximum margin classification with support vector machines  
    5. Solving nonlinear problems using a kernel SVM  
    6. Decision tree learning  
    7. K-nearest neighbors – a lazy learning algorithm 
  4. Building Good Training Datasets – Data Preprocessing
    1. Dealing with missing data
    2. Handling categorical data
    3. Partitioning a dataset into separate training and test datasets
    4. Bringing features onto the same scale
    5. Selecting meaningful features
    6. Assessing feature importance with random forests  
  5. Compressing Data via Dimensionality Reduction  
    1. Unsupervised dimensionality reduction via principal component analysis  
    2. Supervised data compression via linear discriminant analysis  
    3. Using kernel principal component analysis for nonlinear mappings 
  6. Learning Best Practices for Model Evaluation and Hyperparameter Tuning  
    1. Streamlining workflows with pipelines  
    2. Using k-fold cross-validation to assess model performance  
    3. Debugging algorithms with learning and validation curves  
    4. Fine-tuning machine learning models via grid search  
    5. Looking at different performance evaluation metrics  
  7. Combining Different Models for Ensemble Learning
    1. Learning with ensembles
    2. Combining classifiers via majority vote
    3. Bagging – building an ensemble of classifiers from bootstrap samples
    4. Leveraging weak learners via adaptive boosting  
  8. Applying Machine Learning to Sentiment Analysis 
    1. Preparing the IMDb movie review data for text processing  
    2. Introducing the bag-of-words model  
    3. Training a logistic regression model for document classification  
    4. Working with bigger data – online algorithms and out-of-core learning  
    5. Topic modeling with Latent Dirichlet Allocation  
  9. Embedding a Machine Learning Model into a Web Application  
    1. Serializing fitted scikit-learn estimators  
    2. Setting up an SQLite database for data storage  
    3. Developing a web application with Flask  
    4. Turning the movie review classifier into a web application  
    5. Deploying the web application to a public server  
  10. Predicting Continuous Target Variables with Regression Analysis  
    1. Introducing linear regression  
    2. Exploring the Housing dataset  
    3. Implementing an ordinary least squares linear regression model  
    4. Fitting a robust regression model using RANSAC  
    5. Evaluating the performance of linear regression models  
    6. Using regularized methods for regression  
    7. Turning a linear regression model into a curve – polynomial regression  
    8. Dealing with nonlinear relationships using random forests  
  11. Working with Unlabeled Data – Clustering Analysis  
    1. Grouping objects by similarity using k-means  
    2. Organizing clusters as a hierarchical tree  
    3. Locating regions of high density via DBSCAN  
  12. Implementing a Multilayer Artificial Neural Network from Scratch 
    1. Modeling complex functions with artificial neural networks  
    2. Classifying handwritten digits  
    3. Training an artificial neural network  
    4. About the convergence in neural networks  
    5. A few last words about the neural network implementation  
  13. Parallelizing Neural Network Training with TensorFlow  
    1. TensorFlow and training performance  
    2. First steps with TensorFlow  
    3. Building input pipelines using tf.data – the TensorFlow Dataset API  
    4. Building an NN model in TensorFlow  
    5. Choosing activation functions for multilayer neural networks  
  14. Going Deeper – The Mechanics of TensorFlow  
    1. The key features of TensorFlow  
    2. TensorFlow’s computation graphs: migrating to TensorFlow v2  
    3. TensorFlow Variable objects for storing and updating model parameters  
    4. Computing gradients via automatic differentiation and GradientTape  
    5. Simplifying implementations of common architectures via the Keras API  
    6. TensorFlow Estimators  
  15. Classifying Images with Deep Convolutional Neural Networks  
    1. The building blocks of CNNs  
    2. Putting everything together – implementing a CNN  
    3. Implementing a deep CNN using TensorFlow  
    4. Gender classification from face images using a CNN  
  16. Modeling Sequential Data Using Recurrent Neural Networks  
    1. Introducing sequential data  
    2. RNNs for modeling sequences  
    3. Implementing RNNs for sequence modeling in TensorFlow  
    4. Understanding language with the Transformer model  
  17. Generative Adversarial Networks for Synthesizing New Data  
    1. Introducing generative adversarial networks  
    2. Implementing a GAN from scratch  
    3. Improving the quality of synthesized images using a convolutional and Wasserstein GAN  
    4. Other GAN applications  
  18. Reinforcement Learning for Decision Making in Complex Environments  
    1. Introduction – learning from experience  
    2. The theoretical foundations of RL  
    3. Reinforcement learning algorithms  
    4. Implementing our first RL algorithms  

Who should attend

  • This course is geared for Python experienced developers, analysts or others who are intending to apply machine learning with a solid foundation in theory. Revised and expanded for TensorFlow 2, GANs, and reinforcement learning. 
  • Skill-level: Foundation-level Python Machine Learning skills for Intermediate skilled team members. This is not a basic class.  
  • IT skills: Basic to Intermediate (2-5 years’ experience)   
  • Linux: Basic (1-2 years’ experience), including familiarity with command-line options such as ls, cd, cp, and su