Deep Learning with TensorFlow 2.0

BY
Udemy

Master the Tensorflow 2.0 concepts to create deep learning algorithms for your business.

Mode

Online

Fees

₹ 549 3099

Quick Facts

particular details
Medium of instructions English
Mode of learning Self study
Mode of Delivery Video and Text Based

Course overview

Tensorflow is the world's most widely used deep learning framework, and it was created by Google. Tensorflow is the machine learning and artificial intelligence library of preference for many businesses. Deep Learning with TensorFlow 2.0 online certification is created by 365 Careers, an Udemy-affiliated educational platform that creates opportunities for finance and data science students.

Deep Learning with TensorFlow 2.0  online classes offers 6 hours of prerecorded lessons supported by 18 articles and 20 downloadable resources which are targeted at the students interested in mastering the strategies to code and build deep learning algorithms and machine learning algorithms from scratch to become certified data scientists. Deep Learning with TensorFlow 2.0 online training revolves around topics like neural networks, standardization, machine learning, initialization, normalization, pre-processing, training, validation, overfitting, underfitting, and more.

The highlights

  • Certificate of completion
  • Self-paced course
  • 6 hours of pre-recorded video content
  • 18 articles
  • 20 downloadable resources

Program offerings

  • Online course
  • Learning resources
  • 30-day money-back guarantee
  • Unlimited access
  • Accessible on mobile devices and tv

Course and certificate fees

Fees information
₹ 549  ₹3,099
certificate availability

Yes

certificate providing authority

Udemy

What you will learn

Knowledge of deep learning Knowledge of python Knowledge of numpy Machine learning Mathematical skill

After completing the Deep Learning with TensorFlow 2.0 certification course, students will develop an in-depth understanding of the principles of deep learning using TensorFlow and will acquire a deeper understanding of mathematical concepts behind deep learning algorithms. In this deep learning certification, students will explore the functionalities of Python and NumPy and acquire an understanding of the basics of neural networks and machine learning. Students will learn about concepts like backpropagation, batching, normalization, standardization, overfitting, underfitting, one-hot encoding, and initialization. In this deep learning course, students will also learn about concepts involved with momentum, rate schedules, training, validation, testing, early stopping, and preprocessing.

The syllabus

Welcome! Course introduction

  • Meet your instructors and why you should study machine learning?
  • What does the course cover?
  • What does the course cover? - Quiz
  • Download All Resources and Important FAQ

Introduction to neural networks

  • Introduction to neural networks
  • Introduction to neural networks - Quiz
  • Training the model
  • Training the model - Quiz
  • Types of machine learning
  • Types of machine learning - Quiz
  • The linear model
  • The linear model - Quiz
  • Need Help with Linear Algebra?
  • The linear model. Multiple inputs
  • The linear model. Multiple inputs - Quiz
  • The linear model. Multiple inputs and multiple outputs
  • The linear model. Multiple inputs and multiple outputs - Quiz
  • Graphical representation
  • Graphical representation - Quiz
  • The objective function
  • The objective function - Quiz
  • L2-norm loss
  • L2-norm loss - Quiz
  • Cross-entropy loss
  • Cross-entropy loss - Quiz
  • One parameter gradient descent
  • One parameter gradient descent - Quiz
  • N-parameter gradient descent
  • N-parameter gradient descent - Quiz

Setting up the working environment

  • Setting up the environment - An introduction - Do not skip, please!
  • Why Python and why Jupyter?
  • Why Python and why Jupyter? - Quiz
  • Installing Anaconda
  • The Jupyter dashboard - part 1
  • The Jupyter dashboard - part 2
  • Jupyter Shortcuts
  • The Jupyter dashboard - Quiz
  • Installing TensorFlow 2
  • Installing packages - exercise
  • Installing packages - solution

Minimal example - your first machine learning algorithm

  • Minimal example - part 1
  • Minimal example - part 2
  • Minimal example - part 3
  • Minimal example - part 4
  • Minimal example - Exercises

TensorFlow - An introduction

  • TensorFlow outline
  • TensorFlow 2 intro
  • A Note on Coding in TensorFlow
  • Types of file formats in TensorFlow and data handling
  • Model layout - inputs, outputs, targets, weights, biases, optimizer and loss
  • Interpreting the result and extracting the weights and bias
  • Cutomizing your model
  • Minimal example with TensorFlow - Exercises

Going deeper: Introduction to deep neural networks

  • Layers
  • What is a deep net?
  • Understanding deep nets in depth
  • Why do we need non-linearities?
  • Activation functions
  • Softmax activation
  • Backpropagation
  • Backpropagation - visual representation

Backpropagation. A peek into the Mathematics of Optimization

  • Backpropagation. A peek into the Mathematics of Optimization

Overfitting

  • Underfitting and overfitting
  • Underfitting and overfitting - classification
  • Training and validation
  • Training, validation, and test
  • N-fold cross validation
  • Early stopping

Initialization

  • Initialization - Introduction
  • Types of simple initializations
  • Xavier initialization

Gradient descent and learning rates

  • Stochastic gradient descent
  • Gradient descent pitfalls
  • Momentum
  • Learning rate schedules
  • Learning rate schedules. A picture
  • Adaptive learning rate schedules
  • Adaptive moment estimation

Preprocessing

  • Preprocessing introduction
  • Basic preprocessing
  • Standardization
  • Dealing with categorical data
  • One-hot and binary encoding

The MNIST example

  • The dataset
  • How to tackle the MNIST
  • Importing the relevant packages and load the data
  • Preprocess the data - create a validation dataset and scale the data
  • Preprocess the data - scale the test data
  • Preprocess the data - shuffle and batch the data
  • Preprocess the data - shuffle and batch the data
  • Outline the model
  • Select the loss and the optimizer
  • Learning
  • MNIST - exercises
  • MNIST - solutions
  • Testing the model

Business case

  • Exploring the dataset and identifying predictors
  • Outlining the business case solution
  • Balancing the dataset
  • Preprocessing the data
  • Preprocessing exercise
  • Load the preprocessed data
  • Load the preprocessed data - Exercise
  • Learning and interpreting the result
  • Setting an early stopping mechanism
  • Setting an early stopping mechanism - Exercise
  • Testing the model
  • Final exercise

Appendix: Linear Algebra Fundamentals

  • What is a Matrix?
  • Scalars and Vectors
  • Linear Algebra and Geometry
  • Scalars, Vectors and Matrices in Python
  • Tensors
  • Addition and Subtraction of Matrices
  • Errors when Adding Matrices
  • Transpose of a Matrix
  • Dot Product of Vectors
  • Dot Product of Matrices
  • Why is Linear Algebra Useful?

Conclusion

  • See how much you have learned
  • What’s further out there in the machine and deep learning world
  • An overview of CNNs
  • How DeepMind uses deep learning
  • An overview of RNNs
  • An overview of non-NN approaches

Bonus lecture

  • Bonus lecture: Next steps

Trending Courses

Popular Courses

Popular Platforms

Learn more about the Courses

Download the Careers360 App on your Android phone

Regular exam updates, QnA, Predictors, College Applications & E-books now on your Mobile

Careers360 App
150M+ Students
30,000+ Colleges
500+ Exams
1500+ E-books