Certificate in Deep Learning with Keras

Course details

Keras is an open source neural network library written in Python. It is capable of running on top of MXNet, Deeplearning4j, Tensorflow, CNTK, or Theano. Designed to enable fast experimentation with deep neural networks, it focuses on being minimal, modular, and extensible.

Note: Hard copy material is not applicable for this course.

Why should one take Deep Learning with Keras Certification?

This Course is intended for Individuals wanting to understand a deeper level of deep learning using Keras. The course provides you a comprehensive introduction to deep learning, you will also be trained on neural networks and optimization techniques.

Earning Vskills Deep Learning with Keras Certification can help candidate differentiate in today's competitive job market, broaden their employment opportunities by displaying their advanced skills, and result in higher earning potential.

Who will benefit from taking Deep Learning with Keras Certification?
IT specialists aspiring to learn a new skill set; statisticians; computer scientists; and IT analysts etc.

Benefits of Certification

• Government Certification
• Certification valid for life
• Lifelong e-learning access
• Learning Hours: 12+ hrs

 
How It Works

1. Select Certification & Register
2. Receive Online e-Learning Access (LMS)
3. Take exam online anywhere, anytime
4. Get certified & Increase Employability

Test Details

• Duration: 60 minutes
• No. of questions: 50
• Maximum marks: 50, Passing marks: 25 (50%).
• There is NO negative marking in this module.
• Online exam.

 
Table of Content

Introduction to Machine Learning with Keras

• Course Overview
• Installation and Setup
• Lesson Overview
• Data Representation
• Loading a Dataset from the UCI Machine Learning Repository
• Data Pre-Processing
• Cleaning the Data
• Appropriate Representation of the Data
• Lifecycle of Model Creation
• Machine Learning Libraries and scikit-learn
• Keras
• Model Training
• Creating a Simple Model
• Model Tuning
• Regularization

Machine Learning versus Deep Learning

• Lesson Overview
• Introduction to ANNs
• Linear Transformations
• Matrix Transposition
• Introduction to Keras

Deep Learning with Keras

• Lesson Overview
• Building Your First Neural Network
• Gradient Descent for Learning the Parameters
• Model Evaluation

Evaluate Your Model with Cross-Validation using Keras Wrappers

• Lesson Overview
• Cross-Validation
• Cross-Validation for Deep Learning Models
• Evaluate Deep Neural Networks with Cross-Validation
• Model Selection with Cross-validation
• Write User-Defined Functions to Implement Deep Learning Models with Cross-Validation

Improving Model Accuracy

• Lesson Overview
• Regularization
• L1 and L2 Regularization
• Dropout Regularization
• Other Regularization Methods
• Data Augmentation
• Hyperparameter Tuning with scikit-learn

Model Evaluation

• Lesson Overview
• Accuracy
• Imbalanced Datasets
• Confusion Matrix
• Computing Accuracy and Null Accuracy with Healthcare Data
• Calculate the ROC and AUC Curves

Computer Vision with Convolutional Neural Networks

• Lesson Overview
• Computer Vision
• Architecture of a CNN
• Image Augmentation
• Amending Our Model by Reverting to the Sigmoid Activation Function
• Changing the Optimizer from Adam to SGD
• Classifying a New Image

Transfer Learning and Pre-trained Models

• Lesson Overview
• Pre-Trained Sets and Transfer Learning
• Fine Tuning a Pre-Trained Network
• Classification of Images that are not Present in the ImageNet Database
• Fine-Tune the VGG16 Model
• Image Classification with ResNet

Sequential Modeling with Recurrent Neural Networks

• Lesson Overview
• Sequential Memory and Sequential Modeling
• Long Short-Term Memory – LSTM
• Predict the Trend of Apple's Stock Price Using an LSTM with 50 Units (Neurons)
• Predicting the Trend of Apple's Stock Price Using an LSTM with 100 Units

Updated on 21 December, 2023