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.

Machine Learning with TensorFlow

  • Course Code: Artificial Intelligence - Machine Learning with TensorFlow
  • Course Dates: Contact us to schedule.
  • Course Category: AI / Machine Learning Duration: 5 Days Audience: This course is geared for those who wants to learn the foundational concepts of machine learning, and how to utilize the TensorFlow library to rapidly build powerful ML models

Course Snapshot 

  • Duration: 5 days 
  • Skill-level: Foundation-level Machine Learning with TensorFlow skills for Intermediate skilled team members. This is not a basic class. 
  • Targeted Audience: This course is geared for those who wants to learn the foundational concepts of machine learning, and how to utilize the TensorFlow library to rapidly build powerful ML models 
  • Hands-on Learning: This course is approximately 50% hands-on lab to 50% lecture ratio, combining engaging lecture, demos, group activities and discussions with machine-based student labs and exercises. Student machines are required. 
  • Delivery Format: This course is available for onsite private classroom presentation. 
  • Customizable: This course may be tailored to target your specific training skills objectives, tools of choice and learning goals. 

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’ll 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’ve mastered core ML concepts, you’ll 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’ll be able to start modelling your everyday problems as automated machine learning tasks. 

Working in a hands-on learning environment, led by our Machine Learning with TensorFlow expert instructor, students will learn about and explore: 

  • how to utilize the TensorFlow library to rapidly build powerful ML models  
  • You’ll 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’ve mastered core ML concepts  
  • you’ll be able to start modelling your everyday problems as automated machine learning tasks. 

Topics Covered: This is a high-level list of topics covered in this course. Please see the detailed Agenda below 

  • 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 

Audience & Pre-Requisites 

This course is geared for attendees who wants to learn the foundational concepts of machine learning, and how to utilize the TensorFlow library to rapidly build powerful ML models 

Pre-Requisites:  Students should have  

  • Basic to Intermediate IT Skills, and Machine Learning knowledge 
  • Good foundational mathematics or logic skills 
  • experienced with Python and algebraic concepts like vectors and matrices. 

Course Agenda / Topics 

PART 1: YOUR MACHINE-LEARNING RIG 

  1. A machine-learning odyssey 
  • Machine-learning fundamentals 
  • Data representation and features 
  • Distance metrics 
  • Types of learning 
  • TensorFlow 
  1. TensorFlow essentials 
  • 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 

PART 2: CORE LEARNING ALGORITHMS 

  1. Linear regression and beyond 
  • Formal notation 
  • Linear regression 
  • Polynomial model 
  • Regularization 
  • Application of linear regression 
  1. Using regression for call center volume prediction 
  • 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 
  1. A gentle introduction to classification 
  • Formal notation 
  • Measuring performance 
  • Using linear regression for classification 
  • Using logistic regression 
  • Multiclass classifier 
  • Application of classification 
  1. Sentiment classification: Netflix large movie-review dataset 
  • 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 
  1. Automatically clustering data 
  • Traversing files in TensorFlow 
  • Extracting features from audio 
  • K-means clustering 
  • Audio segmentation 
  • Clustering using a self-organizing map 
  • Application of clustering 
  1. Inferring user activity from Android accelerometer data 
  • 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 
  1. Hidden Markov models 
  • 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 
  1. Part of speech tagging and word sense disambiguation 
  • 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 

PART 3: THE NEURAL NETWORK PARADIGM 

  1. A peek into autoencoders 
  • Neural networks 
  • Autoencoders 
  • Batch training 
  • Working with images 
  • Application of autoencoders 
  1. Applying autoencoders: the CIFAR- image dataset 
  1. Reinforcement learning 
  1. Convolutional neural networks 
  1. Building a real-world CNN: VGG-Face and VGG-Face Lite 
  1. Recurrent neural networks 
  1. LSTMs and automatic speech recognition  
  1. Sequence-to-sequence models for chatbots 
  1. Utility landscape 
View All Courses

    Course Inquiry

    Fill in the details below and we will get back to you as quickly as we can.

    Interested in any of these related courses?