Deep Learning For Absolute Beginners

Deep Learning For Absolute Beginners, available at $19.99, with 32 lectures, and has 5 subscribers.

You will learn about Create computer vision system using Deep Learning. Build you own dataset from scratch. Use algorithms like CNN and transfer learning techniques to quickly create deep learning system with less data. Code first approach towards Deep Learning. This course is ideal for individuals who are Beginners interested in Deep Learning. or Experienced coders interested in Deep Learning. or Non coders who are curious to learn Deep Learning. or Other curious minds. It is particularly useful for Beginners interested in Deep Learning. or Experienced coders interested in Deep Learning. or Non coders who are curious to learn Deep Learning. or Other curious minds.

Enroll now: Deep Learning For Absolute Beginners

Summary

Title: Deep Learning For Absolute Beginners

Price: $19.99

Number of Lectures: 32

Number of Published Lectures: 32

Number of Curriculum Items: 32

Number of Published Curriculum Objects: 32

Original Price: ₹1,199

Quality Status: approved

Status: Live

What You Will Learn

Create computer vision system using Deep Learning.
Build you own dataset from scratch.
Use algorithms like CNN and transfer learning techniques to quickly create deep learning system with less data.
Code first approach towards Deep Learning.

Who Should Attend

Beginners interested in Deep Learning.
Experienced coders interested in Deep Learning.
Non coders who are curious to learn Deep Learning.
Other curious minds.

Target Audiences

Beginners interested in Deep Learning.
Experienced coders interested in Deep Learning.
Non coders who are curious to learn Deep Learning.
Other curious minds.

We all have this impression that to do deep learning we need to have a Phd or a degree in Machine learning. Well! this is not true. All you need is an interest to try out new things and step into a new territory of learning. You also don’t need fancy hardware to start with as all that you need is already available on the cloud and many timea these are free of cost.

In this course you will learn how to create neural networks with few lines of code and how can we use transfer learning to use less data than usual. The idea here is to learn with a top down approach i.e. build something and hack into it to learn what goes on under the hood. This way learning becomes interesting and fruitful.

This course is perfect for you if you are someone who wants to step into the fabulous world of deep learning. This course aims to be jargon free and simplistic in approach so that learning doesn’t feel overwhelming.

This course has step by step instructions alongwith all the relevant code baked into each part of the course. Loads of examples with interesting usecase is what you can find here.

Course Curriculum

Chapter 1: Introduction

Lecture 1: Introduction

Chapter 2: How to Build Your Own Dataset For Deep Learning

Lecture 1: First set image scraping

Lecture 2: Second image set download

Lecture 3: Where to find the code related to all the lectures.

Chapter 3: Pre-processing The Training Data

Lecture 1: Downloading The Data

Lecture 2: Cleaning downloaded data

Chapter 4: Setting Up The Workspace

Lecture 1: importing data to kaggle

Lecture 2: Importing necessary modules

Chapter 5: Data Augmentation And Mini batch Preparation For Training

Lecture 1: Select input path

Lecture 2: Select correct files for training

Lecture 3: Creating Databunch

Chapter 6: How To Do Deep Learning With Little Data

Lecture 1: How To Deal With Data Shortage

Lecture 2: What Is Transfer Learning and How It Works

Chapter 7: Creating A Neural Network with one line of code

Lecture 1: Create a CNN with one line of code

Lecture 2: How A CNN Works

Chapter 8: What Is Pre-Training And How To Use It

Lecture 1: Importing A Pre Trained Model

Lecture 2: Loading Pre-trained Model

Lecture 3: Using A Pre-Trained Model

Chapter 9: Training A Neural Network With Few Lines Of Code

Lecture 1: Analyzing The Created Model

Lecture 2: Training A Neural Network With Few Lines Of Code

Chapter 10: Testing The Model

Lecture 1: Testing The Created Model

Lecture 2: Saving The Model

Chapter 11: Visualizing Model Performance

Lecture 1: Plotting The Confusion Matrix And Visualizing Model Performance

Lecture 2: Analyzing Current Performance Of Model

Chapter 12: Advanced Technique- What Is Learning Rate And How To Use It

Lecture 1: What Is Learning Rate

Lecture 2: Visualizing How to Find The Learning Rate

Lecture 3: Using Optimal Learning Rate

Chapter 13: Advanced Technique- Checking Performance Of The Model

Lecture 1: Checking The Performance Of The Model And Saving The Model

Chapter 14: Advanced Concept- A Visual Way To Understand Internals Of A CNN

Lecture 1: Visualizing How A CNN Perceives An Image

Lecture 2: Diving Deep Into The Internal Working Of A CNN

Chapter 15: Advanced Tricks To Build Computationally Efficient Neural Network

Lecture 1: Techniques To Deal With Unexpected Image Sizes

Lecture 2: Advance Technique To Create Computationaly Efficient Neural Network

Instructors

Satyabrata Pal
Software Test Analyst at FIS, Volunteer at Coronawhy.org

Rating Distribution

1 stars: 0 votes
2 stars: 0 votes
3 stars: 0 votes
4 stars: 0 votes
5 stars: 0 votes

Frequently Asked Questions

How long do I have access to the course materials?

You can view and review the lecture materials indefinitely, like an on-demand channel.

Can I take my courses with me wherever I go?

Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don’t have an internet connection, some instructors also let their students download course lectures. That’s up to the instructor though, so make sure you get on their good side!

Menu