Machine Learning & Deep Learning : Python Practical Hands-on

Name: Machine Learning & Deep Learning : Python Practical Hands-on
Rating: 4.5 (89 reviews)

Code, Develop, Validate & Deploy Machine Learning & Keras Deep Learning Neural Network Models.

Created byAbilash Nair

Last updated 9/2024

English

What you'll learn

Basics to Advanced Machine Learning & Advanced Deep Learning Algorithms with Live Practice Interviews with Experts
Image Recognition & Keras Deep Learning Neural Network Model Implementation.
Automated Machine Learning Frameworks & Model Deployment Architectures
Basic to Advanced Python with Pandas and Flask API creation
Anomaly Detection Algorithms
Efficient Feature Engineering & Data Pre-Processing
Working with Multiple Data Sets and Algorithm building in Kaggle Cloud.
Deep Learning Encoder Decoder Models

Course content

16 sections • 80 lectures • 10h 50m total length

Course Introduction - About the course0:54
Introduction to Machine Learning Concepts7:08
Types of Machine Learning4:45
Types of Supervised Methods - Regression & Classification4:01
More examples on Regression and Classification4:29
Machine Learning Algorithms2:31
Concepts Quiz
Stages of Machine Learning Project Life Cycle9:42
Concepts Quiz
Architecture : Machine Learning Model Deployment in Production8:11

Introduction to Anaconda & Jupiter - Python IDE5:05
Anaconda & Jupyter notebook usage shown. Students familiar with anaconda, jupyter notebooks and python basics can skip and work on pandas directly.
Python Strings , Numbers and Data Types12:17
Jupyter file with code is attached in this lecture as Downloadable materials. Please download and upload to jupyter as showcased in previous video. Once uploaded, open the code file and execute it step by step as mentioned in the python training video.
Python Logical Operations & Conditional Statements22:20
Python Logical Operations & Conditional Statements24:34
Python Reusable Code Functions3:34
API call pre data conditioning with JSON8:41
API call , Request and Response, Shallow & Deep Copy21:57
Exception Handling9:12
Jupyter file with code is attached in this lecture as Downloadable materials. Please download and upload to jupyter. Once uploaded, open the code file and execute it step by step as mentioned in the python training video.
Coding Challenge
Coding Challenge

Flask introduction3:56
Flask Request and Response8:11
Download the code file and template.zip(unzip it for sure) and place them in D:/web-project or any suitable folder of your choice. Make sure to rename the folder path in code in case using some other folder path.
Flask File Upload5:07
Model Prediction API Request with Flask8:24
This shows the flask capability to take request parameters from client(UI) and pass to model for prediction and return the predicted response again to client by flask. Note: *** We will be studying the model building and prediction in our next sections ***. This video just showcase the flask capabilities which would be helpful for deployment of models.
Create a flask request to get the highest number from the list of numbers

Pandas Framework - Read Data Files - csv & excel Files using Pandas9:05
Jupyter file with code is attached in this lecture as Downloadable materials. Please download and upload to jupyter as showcased in previous video. Once uploaded, open the code file and execute it step by step as mentioned in the python training video.
Cancer Dataset is also attached as downloadable material.
Pandas Framework - Filter Data in Data Frames14:04
Pandas Framework - Drop Columns & Datatypes11:14
Pandas Framework - Group Operations on Data5:12
Pandas Framework - Concat Operations on Data10:00
Database Query with Pandas13:54
Code Challenge - Data Processing

Euclidian Distance between points3:51
Algorithm : K- Nearest Neighbor (KNN) Classification6:20
Algorithm : K- Nearest Neighbor (KNN) Regressor3:20
Distance Metric Quiz
Error & Accuracy Calculation Quiz
Sampling Quiz
Kaggle Cloud Platform Introduction3:22
Project Code : KNN Classifier Model Training & Validation12:20
The Kaggle link for the code implementation of the project is attached as resource link.
Model Creation to Predict Species
Project Code : KNN Regressor Model Training & Validation12:04
The Kaggle link for the code implementation of the project is attached as resource link.
Model Creation to Predict Insurance Premium

Algorithm : Linear Regression - Find the Best Linear Model Equation9:27
Algorithm : Linear Regression - Elements of Linear Model and Prediction Strategy8:43
Project Code : Develop Linear Regression Model22:17
Refer to the Kaggle Code Source below or check the external resources link provided.
https://www.kaggle.com/anunnikrishnan/second-hand-price-prediction-linear-regression
Concepts Quiz on Linear Models

Unsupervised Machine Learning Introduction3:01
Algorithm: K- Means Clustering4:17
Algorithm: K- Means Clustering Elbow Method3:38
Unsupervised Concepts Quiz
Project Code : K-Means Clustering Model - Part 1 Training10:52
The Kaggle link for the code implementation of the project is attached as resource link.
Project Code : K-Means Clustering Model - Part 2 Training10:14
Financial Analysis Model - Customer Credit Card Patterns Analysis
Concepts Quiz

Requirements

Willingness to Learn
Basics of Python may be good to have but not mandatory

Description

Interested in the field of Machine Learning? Then this course is for you!

Designed & Crafted by AI Solution Expert with 15 + years of relevant and hands on experience into Training , Coaching and Development.

Complete Hands-on AI Model Development with Python.
Course Contents are:
1. Understand Machine Learning in depth and in simple process.
2. Fundamentals of Machine Learning
3. Understand the Deep Learning Neural Nets with Practical Examples.
4. Understand Image Recognition and Auto Encoders.
5. Machine learning project Life Cycle
6. Supervised & Unsupervised Learning
7. Data Pre-Processing
8. Algorithm Selection
9. Data Sampling and Cross Validation
10. Feature Engineering
11. Model Training and Validation
12. K -Nearest Neighbor Algorithm
13. K- Means Algorithm
14. Accuracy Determination
15. Visualization using Seaborn
You will be trained to develop various algorithms for supervised & unsupervised methods such as KNN , K-Means , Random Forest, XGBoost model development.
Understanding the fundamentals and core concepts of machine learning model building process with validation and accuracy metric calculation. Determining the optimum model and algorithm.
Cross validation and sampling methods would be understood.
Data processing concepts with practical guidance and code examples provided through the course.
Feature Engineering as critical machine learning process would be explained in easy to understand and yet effective manner.
We will walk you step-by-step into the World of Machine Learning. With every tutorial, you will develop new skills and improve your understanding of this challenging yet lucrative sub-field of Data Science.
Moreover, the course is packed with practical exercises that are based on real-life examples. So not only will you learn the theory, but you will also get some hands-on practice building your own models.

Who this course is for:

This course is designed for Beginners and Freshers in Data Science
This course will lay strong foundation of Machine Learning & Deep Learning

Machine Learning & Deep Learning : Python Practical Hands-on

What you'll learn

Explore related topics

Course content

Machine Learning Introduction & AI Project Life Cycle.8 lectures • 42min

Feature Engineering Process - Most Critical Process3 lectures • 11min

Determine Best Machine Learning Model - Accuracy & Error Understanding Process2 lectures • 10min

Code - Python Crash Course - Quick Deep Dive to Python Fundamentals8 lectures • 1hr 48min

API creation with Web framework Flask4 lectures • 26min

Code - Data Processing with Powerful Pandas Framework6 lectures • 1hr 3min

Algorithm - K-Nearest Neighbor (KNN) - Supervised Learning6 lectures • 41min

Algorithm: Linear Regression - Supervised Learning3 lectures • 40min

Algorithm - Support Vector Machines (SVM) - Supervised Learning4 lectures • 24min

Algorithm - K - Means - Unsupervised Learning5 lectures • 32min

Requirements

Description

Who this course is for: