Back to Lobby

Applied Machine Learning using Python and TensorFlow

IntML - Version:2
in this 5-day course we will go over basic concepts in machine learning. Learn the development and deployment procedure. Learn statistical tools for evaluating our results. Learn How to use with hands-on practice in building such systems based on python. Learn about Supervised machine learning models and how they work. Learn about Neural Nets: How to build them, manipulate them and train them using Google's recommended package of tensorFlow.
Intended audience
This course is intended for algorithm engineer, IT developers, digital marketers, CTO, business analysts who are taking their first steps with data science, data mining and machine learning in order to provides them the required skills for becoming a productive data scientist in that environment. The course is suitable for people who planning to engage in data science and big data analytics projects. The course gives hands-on practice in python Sklearn and TenzorFlow and AzurML. Learning the fundamentals as well as advanced features.
Expand All
  • Basic Concepts

    • Supervised learning: classification vs. regression
    • Unsupervised Learning
    • Structured learning: Bayesian networks
    • Reinforcement Learning and Markovian random fields
  • Data Preparation

    • Data normalization
    • Imputation
    • Feature selection
    • Dimensionality reduction (PCA, LDA , Tree based)
  • Learning Theory

    • Overfitting vs. underfitting in practice
    • Learning curves and validation curves their power as analytical tools
    • Bias vs. variance decomposition
    • Regularization
  • Model Selection
  • Statistical Models

    • Decision trees
    • KNN (K-nearest neighbors)
    • Naive Bayes
    • Ensemble models (Random Forest, Bagging and Boosting)
  • Linear Models

    • Linear regression
    • Logistic regression
    • Perceptron
    • The principle of working in higher dimensions
    • SVM
    • Kernel SVM
  • Scikit Learn Package Overview
  • Deep Learning

    • Introduction to Neural Nets
    • Convolutional NN
    • CNN architecture and pretrained models
    • Recurrent NN
    • LSTM and GRU Networks
  • Introduction to Tenzorflow, Layers , Keras
  • Engineering/scientific/mathematical
  • Academic background
  • Soft skills in programing and statistics.
  • Experience working with python advantage.
  • Describe basic concepts in machine learn
  • Be able to tune train and select models for machine learning
  • Develop programs in the industry most advanced tools
  • Configure and adjust applications to machine learning
Contact Us


Related Courses