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.

banner-img

Course Skill Level:

Foundational to Intermediate

Course Duration:

5 day/s

  • Course Delivery Format:

    Live, instructor-led.

  • Course Category:

    AI / Machine Learning

  • Course Code:

    MLTENFL21E09

Who should attend & recommended skills:

Those with machine learning foundation, basic IT skills, intermediate Python and algebraic concepts knowledge

Who should attend & recommended skills

  • This course is geared for those who want to learn the foundational concepts of machine learning, and how to utilize the TensorFlow library to rapidly build powerful ML models.
  • Skill-level: Foundation-level Machine Learning with TensorFlow skills for Intermediate skilled team members. This is not a basic class.
  • IT skills: Basic to Intermediate (1+ years’ experience)
  • Machine Learning: Basic to Intermediate (1+ years’ experience)
  • Python: Intermediate (3+ years’ experience)
  • Algebraic concepts like vectors and matrices: Experienced: (3+ years’ experience)

About this course

This fully revised edition of Machine Learning with TensorFlow teaches you the foundational concepts of machine learning, and how to utilize the TensorFlow library to rapidly build powerful ML models. You will learn the basics of regression, classification, and clustering algorithms, applying them to solve real-world challenges such as call center volume prediction and sentiment analysis of movie reviews. Once you have mastered core ML concepts, you will move on to the money lessons: exploring cutting-edge neural network techniques such as deep speech classifiers, facial identification, and auto-encoding with CIFAR-10. Digest this course, and you will be able to start modelling your everyday problems as automated machine learning tasks.

Skills acquired & topics covered

  • How to utilize the TensorFlow library to rapidly build powerful ML models
  • Basics of regression, classification, and clustering algorithms, applying them to solve real-world challenges such as call center volume prediction and sentiment analysis of movie reviews. Once you’ve mastered core ML concepts
  • Modelling your everyday problems as automated machine learning tasks.
  • Matching your tasks to the right machine-learning or deep-learning approach
  • Visualizing algorithms with Tensor Board
  • Sharing your results with collaborators using other frameworks
  • Understanding and using neural networks
  • Reproducing and employing predictive science
  • Downloadable Jupyter Notebooks for all examples
  • Questions to test your knowledge
  • Examples use the super-stable 1.14.1 branch of TensorFlow

Course breakdown / modules

  • Machine-learning fundamentals
  • Data representation and features
  • Distance metrics
  • Types of learning
  • TensorFlow

  • Ensuring that TensorFlow works
  • Representing tensors
  • Creating operators
  • Executing operators with sessions
  • Understanding code as a graph
  • Writing code in Jupyter
  • Using variables
  • Saving and loading variables
  • Visualizing data using TensorBoard
  • Putting it all together: The TensorFlow System Architecture and. API

  • Formal notation
  • Linear regression
  • Polynomial model
  • Regularization
  • Application of linear regression

  • What is 3-1-1?
  • Cleaning the data for regression
  • What’s in a bell curve: predicting Gaussian distributions
  • Training your call prediction regressor
  • Visualizing the results and plotting the error
  • Regularization and train test splits

  • Formal notation
  • Measuring performance
  • Using linear regression for classification
  • Using logistic regression
  • Multiclass classifier
  • Application of classification

  • The Bag of Words model
  • Analysis on your Bag of Words
  • Building a sentiment classifier using logistic regression
  • Making predictions using your sentiment classifier
  • Measuring the effectiveness of your classifier
  • Creating the softmax-regression sentiment classifier
  • Submit your results to Kaggle

  • Traversing files in TensorFlow
  • Extracting features from audio
  • K-means clustering
  • Audio segmentation
  • Clustering using a self-organizing map
  • Application of clustering

  • The user activity from walking dataset
  • Clustering similar participants based on jerk magnitudes
  • Different classes of user activity for a single participant: climbing, standing, walking, talking, and working

  • Example of a not-so-interpretable model
  • Markov model
  • Hidden Markov model
  • Forward algorithm
  • Viterbi decoding
  • Uses of hidden Markov models
  • Application of hidden Markov models

  • Review the HMM example: rainy or sunny and what it’s actually doing
  • Part-of-speech tagging
  • Algorithms for building the Hidden Markov Model for PoS disamguiation
  • Running the HMM and evaluating its output
  • Getting more training data using the Brown corpus
  • Defining error bars and metrics for PoS tagging

  • Neural networks
  • Autoencoders
  • Batch training
  • Working with images
  • Application of autoencoders