Course Description

  • What are the course objectives?

    Deep Learning is one of the most exciting and promising segments of Artificial Intelligence and machine learning technologies. This deep learning course with TensorFlow is designed to help you master deep learning techniques and build deep learning models using TensorFlow, the open-source software library developed by Google for the purpose of conducting machine learning and deep neural networks research. It is one of the most popular software platforms used for deep learning and contains powerful tools to help you build and implement artificial neural networks.
     
    Advancements in deep learning are being seen in smartphone applications, creating efficiencies in the power grid, driving advancements in healthcare, improving agricultural yields, and helping us find solutions to climate change. With this Tensorflow course, you’ll build expertise in deep learning models, learn to operate TensorFlow to manage neural networks and interpret the results.
     
    And according to payscale.com, the median salary for engineers with deep learning skills tops $120,000 per year.
     
    What are the course objectives

  • What skills will you learn with this Deep Learning course?

    By the end of this deep learning course with TensorFlow, you will be able to accomplish the following:

    • Understand the concepts of TensorFlow, its main functions, operations and the execution pipeline
    • Implement deep learning algorithms, understand neural networks and traverse the layers of data abstraction which will empower you to understand data like never before
    • Master and comprehend advanced topics such as convolutional neural networks, recurrent neural networks, training deep networks and high-level interfaces
    • Build deep learning models in TensorFlow and interpret the results
    • Understand the language and fundamental concepts of artificial neural networks
    • Troubleshoot and improve deep learning models
    • Build your own deep learning project
    • Differentiate between machine learning, deep learning and artificial intelligence

  • Who should take this Deep Learning with TensorFlow course?

    There is booming demand for skilled deep learning engineers across a wide range of industries, making this deep learning course with TensorFlow training well-suited for professionals at the intermediate to advanced level of experience. We recommend this deep learning online course particularly for the following professionals: 
    • Software engineers
    • Data scientists
    • Data analysts
    • Statisticians with an interest in deep learning

  • What projects are included in this Deep Learning Online Training Course?

    The course includes the following industry-based project. Successful evaluation of the following project is a part of the certification eligibility criteria:

    Project 1: Pet Classification Model Using CNN

    In this project, you build a CNN model that classifies the given pet images correctly into dog and cat images. The code template is given with essential code blocks. TensorFlow can be used to train the data and calculate the accuracy score on the test data.

  • What are the prerequisites for this Deep Learning online course?

    Participants in this Deep Learning online course should have:

    • Familiarity with programming fundamentals
    • Fair understanding of basics of statistics and mathematics

Course Preview

    • Lesson 2 - Introduction to Tensorflow

      31:55
      • 2.1 Learning Objectives
        07:00
      • 2.2 Introduction to TensorFlow
        07:00
      • 2.3 TensorFlow's Hello World
        03:28
      • 2.4 Tensorflow Hello World
      • 2.5 Linear Regression With Tensorflow
      • 2.6 Logistic Regression With Tensorflow
      • 2.7 Activation Functions
      • 2.8 Intro to Deep Learning
        02:39
      • 2.9 Deep Neural Networks
        11:48
    • Lesson 3 - Convolutional Networks

      21:51
      • 3.1 Learning Objectives
      • 3.2 Intro to Convolutional Networks
        04:37
      • 3.3 CNN for Classifications
        04:09
      • 3.4 CNN Architecture
        13:05
      • 3.5 Understanding Convolutions
      • 3.6 CNN with MNIST Dataset
    • Lesson 4 - Recurrent Neural Network

      24:43
      • 4.1 Learning Objectives
        03:06
      • 4.2 The Sequential Problem
        03:06
      • 4.3 The RNN Model
        05:28
      • 4.4 The LSTM Model
        05:25
      • 4.5 Applying RNNs to Language Modeling
        07:38
      • 4.6 LTSM Basics
      • 4.7 MNIST Data Classification With RNN/LSTM
      • 4.8 Applying RNN/LSTM to Language Modelling
      • 4.9 Applying RNN/LSTM to Character Modelling
    • Lesson 5 - Restricted Boltzmann Machines (RBM)

      14:14
      • 5.1 Learning Objectives
        04:29
      • 5.2 Intro to RBMs
        04:29
      • 5.3 Training RBMs
        05:16
      • 5.4 RBM MNIST
      • 5.5 Collaborative Filtering With RBM
    • Lesson 6 - Autoencoders

      17:20
      • 6.1 Learning Objectives
        04:51
      • 6.2 Intro to Autoencoders
        04:51
      • 6.3 Applying RNNs to Language Modelling
        07:38
      • 6.4 Autoencoders
      • 6.5 DBN MNIST
    • Lesson 1 - Welcome!

      02:06
      • 1.1 Welcome!
        02:06
      • 1.2 Learning Objectives
    • Lesson 7 - Course Summary

      02:17
      • 7.1 Course Summary
        02:17
      • Unlocking IBM Certificate
    • Lesson 1 - Course introduction

      • Introduction
    • Lesson 2 - AI and Deep learning introduction

      • What is AI and Deep learning
      • Brief History of AI
      • Recap: SL, UL and RL
      • Deep learning : successes last decade
      • Demo & discussion: Self driving car object detection
      • Applications of Deep learning
      • Challenges of Deep learning
      • Demo & discussion: Sentiment analysis using LSTM
      • Fullcycle of a deep learning project
      • Key Takeaways
      • Knowledge Check
    • Lesson 3 - Artificial Neural Network

      • Biological Neuron Vs Perceptron
      • Shallow neural network
      • Training a Perceptron
      • Demo code: Perceptron ( linear classification) (Assisted)
      • Backpropagation
      • Role of Activation functions & backpropagation
      • Demo code: Backpropagation (Assisted)
      • Demo code: Activation Function (Unassisted)
      • Optimization
      • Regularization
      • Dropout layer
      • Key Takeaways
      • Knowledge Check
      • Lesson-end Project (MNIST Image Classification)
    • Lesson 4 - Deep Neural Network & Tools

      • Deep Neural Network : why and applications
      • Designing a Deep neural network
      • How to choose your loss function?
      • Tools for Deep learning models
      • Keras and its Elements
      • Demo Code: Build a deep learning model using Keras (Assisted)
      • Tensorflow and Its ecosystem
      • Demo Code: Build a deep learning model using Tensorflow (Assisted)
      • TFlearn
      • Pytorch and its elements
      • Key Takeaways
      • Knowledge Check
      • Lesson-end Project: Build a deep learning model using Pytorch with Cifar10 dataset
    • Lesson 5 - Deep Neural Net optimization, tuning, interpretability

      • Optimization algorithms
      • SGD, Momentum, NAG, Adagrad, Adadelta , RMSprop, Adam
      • Batch normalization
      • Demo Code: Batch Normalization (Assisted)
      • Exploding and vanishing gradients
      • Hyperparameter tuning
      • Interpretability
      • Key Takeaways
      • Knowledge Check
      • Lesson-end Project: Hyperparameter Tunning With Keras Tuner
    • Lesson 6 - Convolutional Neural Network

      • Success and history
      • CNN Network design and architecture
      • Demo code: CNN Image Classification (Assisted)
      • Deep convolutional models
      • Key Takeaways
      • Knowledge Check
      • Lesson-end Project: Image Classification
    • Lesson 7 - Recurrent Neural Networks

      • Sequence data
      • Sense of time
      • RNN introduction
      • LSTM ( retail sales dataset kaggle)
      • Demo code: Stock Price Prediction with LSTM (Assisted)
      • Demo code: Multiclass Classification using LSTM (Unassisted)
      • Demo code: Sentiment Analysis using LSTM (Assisted)
      • GRUs
      • LSTM Vs GRUs
      • Key Takeaways
      • Knowledge Check
      • Lesson-end Project: Stock Price Forecasting
    • Lesson 8 - Autoencoders

      • Introduction to Autoencoders
      • Applications of Autoencoders
      • Autoencoder for anomaly detection
      • Demo code: Autoencoder model for MNIST data (Assisted)
      • Key Takeaways
      • Knowledge Check
      • Lesson-end Project: Anomaly detection with Keras
    • Practice Projects

      • PUBG Players Finishing Placement Prediction
    • Math Refresher

      30:36
      • Math Refresher
        30:36
    • Lesson 1 - Learning Objectives

      • Learning Objectives
    • Lesson 2 - Introduction to Deep Learning

      22:31
      • Learning Objectives
      • 1.1 Deep Learning: The Series Introduction
        03:46
      • 1.2 What is a Neural Network
        06:28
      • 1.3 Three Reasons to go Deep
        03:56
      • 1.4 Your choice of Deep Net
        02:58
      • 1.5 An Old Problem
        05:23
    • Lesson 3 - Deep Learning Models

      22:56
      • Learning Objectives
      • 2.1 Restricted Boltzmann Machines
        04:50
      • 2.2 Deep Belief Nets
        04:31
      • 2.3 Convolutional Nets
        08:15
      • 2.4 Recurrent Nets
        05:20
    • Lesson 4 - Additional Deep Learning Models

      19:13
      • Learning Objectives
      • 3.1 Autoencoders
        03:51
      • 3.2 Recursive Neural Tensor Nets
        05:49
      • 3.3 Use Cases
        09:33
    • Lesson 5 - Deep Learning Platforms & Libraries

      25:37
      • Learning Objectives
      • 4.1 What is a Deep Net Platform?
        03:41
      • 4.2 H2O.ai
        03:42
      • 4.3 Dato GraphLab
        03:32
      • 4.4 What is a Deep Learning Library?
        01:58
      • 4.5 Theano
        03:21
      • 4.6 Caffe
        02:48
      • 4.7 Tensorflow
        06:35
      • Unlocking IBM Certificate
    • {{childObj.title}}

      • {{childObj.childSection.chapter_name}}

        • {{lesson.title}}
      • {{lesson.title}}

    View More

    View Less

Exam & Certification

  • What do I need to do to unlock my Simplilearn certificate?

    To obtain the Deep Learning with TensorFlow certification for Online Classroom, you will need to:
    • Attend one complete batch
    • Complete and attain evaluation of any one of the given projects

  • Who provides the certification and how long is it valid for?

    Upon successful completion of the Deep Learning online training course, you will be awarded an industry-recognized course completion certificate from Simplilearn which has a lifelong validity.

  • What are the system requirements to attend the training sessions?

    Minimum system requirements for attending this course are-

    • 8 core processor
    • 32 GB RAM

    Reviews

    A.Anthony Davis
    A.Anthony Davis Kingston

    The Simplilearn Data Scientist Master’s Program is an awesome course! You learn how to solve real-world problems, and the wide variety of projects give you hands-on experience to make you industry-ready. The lecturers are experts and share their knowledge energetically. Thank you for an excellent learning experience.

    Read more Read less
    Abhishek Tripathi
    Abhishek Tripathi Bangalore

    Good online content for data science. I completed Data Science with R and Python. The instructors have good knowledge on the subject. Self-learning videos help a lot, too. Thanks, Simplilearn.

    Read more Read less
    Angiras Modak
    Angiras Modak Associate System Engineer at IBM India Pvt. Ltd., Kolkata

    Simplilearn is one of the best online training providers available. The trainer was really great in explaining the concepts to the minute detail and also gave multiple real-world examples. The course content was very informative. I understood the concept of CNN. Overall I really enjoyed the training a lot.

    Read more Read less

        FAQs

        • What if I miss a class?

          Simplilearn provides recordings of each class so you can review them as needed before the next session. With Flexi-pass, Simplilearn gives you access to all classes for 90 days so that you have the flexibility to choose sessions as per your convenience.

        • Who are the instructors and how are they selected?

          All of our highly qualified trainers are industry experts with years of relevant industry experience. Each of them has gone through a rigorous selection process that includes profile screening, technical evaluation, and a training demo before they are certified to train for us. We also ensure that only those trainers with a high alumni rating remain on our faculty.

        • How will the labs be conducted?

          Simplilearn provides Integrated labs for all the hands-on and projects execution. The learners will be guided on all aspects, from deploying tools to executing hands-on exercises.

        • What is Global Teaching Assistance?

          Our teaching assistants are a dedicated team of subject matter experts here to help you get certified in your first attempt. They engage students proactively to ensure the course path is being followed and help you enrich your learning experience, from class onboarding to project mentoring and job assistance. Teaching Assistance is available during business hours.  

        • Is this live training or will I watch pre-recorded videos?

          The Deep Learning online training is conducted through live streaming. They are interactive sessions that enable you to ask questions and participate in discussions during class time. We do, however, provide recordings of each session you attend for your future reference. Classes are attended by a global audience to enrich your learning experience.

        • What is covered under the 24/7 Support promise?

          We offer 24/7 support through email, chat, and calls. We also have a dedicated team that provides on-demand assistance through our community forum. What’s more, you will have lifetime access to the community forum, even after completion of your course with us.

        • What is Online Classroom training?

          All of the classes are conducted via live online streaming. They are interactive sessions that enable you to ask questions and participate in discussions during class time.

        • Do you provide a money back guarantee for the training programs?

          Yes. We do offer a money-back guarantee for many of our training programs. Refer to our Refund Policy and submit refund requests via our Help and Support portal.

        • How do I enrol for the online training?

          You can enrol for this Deep Learning online training on our website and make an online payment using any of the following options: 
          • Visa Credit or Debit Card
          • MasterCard
          • American Express
          • Diner’s Club
          • PayPal
          Once payment is received you will automatically receive a payment receipt and access information via email.

        • If I need to cancel my enrollment, can I get a refund?

          Yes, you can cancel your enrollment if necessary. We will refund the course price after deducting an administration fee. To learn more, please read our Refund Policy.
           

        • How can I learn more about this training program?

          Contact us using the form on the right of any page on the Simplilearn website, or select the Live Chat link. Our customer service representatives can provide you with more details.
           

                • Disclaimer
                • PMP, PMI, PMBOK, CAPM, PgMP, PfMP, ACP, PBA, RMP, SP, and OPM3 are registered marks of the Project Management Institute, Inc.