5.00
(2 Ratings)
AI ka Chilla 2023- (Complete Artificial Intelligence Course in 40 Days)
By Dr. Aammar Tufail
Categories: AI
About Course
This is a paid premium course, you may learn about free courses on our website go to the following link.
What Will You Learn?
- Artificial intelligence
- Machine learning
- Deep Learning
- Prompt Engineering
- AI apps development
- Portfoliop for AI jobs
Course Content
Pre-requisite
To learn from this course, please finish the pre requisites.
Introduction to Artificial Intelligence (AI)
This section will lay down you understanding about AI
- 00:00
- 00:00
- 00:00
- 00:00
- 00:00
Will me job be replaced by AI?
00:00
Main Goals of this course
Software for this course
Why Do you need to learn pyhton for AI?
00:00Software installation and websites for this course
00:00Conda Environments (A-Z)
00:00VScode setup for python for AI and Data Science
00:00
Python-101 (Complete for AI and Data Science)
Important Lecture before the next ones.
00:00First Line of code in python
00:00Variables in Python
00:00Operator in python
00:00Data Types in Python
00:00Indentations and if conditions in Python
00:00User input program in python
00:00Data structures and indexing in python
00:00Control flow statements in python
00:00Nested Loops in Python
00:00Functions & Lmbda funtions in Python
00:00Modules and Libraries in Python
00:00Types of Errors in Python
00:00Jupyter Notebook and File Handling in Python
00:00MarkDown Crash Course for using jupyter notebooks
00:00
How Data is fueling AI?
Importance of Data in AI
00:00Data and AI ka jor
00:00
ABC of Statistics
ABC of Statistics (Part-1)
00:00ABC of Statistics (Part-2)
00:00ABC of Statistics (Part-3)
00:00ABC of Statistics (Part-4)
00:00ABC of Statistics (Part-5)
00:00ABC of Statistics (Part-6)
00:00ABC of Statistics (Part-7)
00:00ABC of Statistics (Part-8)
00:00ABC of Statistics (Part-9)
00:00
Exploratory Data Analysis (EDA)
Exploratory Data Analysis (EDA) is the process of analyzing data to gain insights and understanding of the data set. This process can help uncover relationships, patterns, and trends in the data, which can lead to better decision making. In Python, EDA can be done using various libraries such as pandas, Matplotlib, and Seaborn. With pandas, you can analyze and manipulate datasets with its built-in functions and tools. Matplotlib and Seaborn allow you to visualize the data in different ways, such as scatter plots, bar graphs, and histograms. Additionally, Python also provides packages such as SciPy and StatsModels for performing statistical analysis, which can be used to test hypotheses and build machine learning models. With the vast amount of tools available in Python, EDA can be performed quickly and efficiently.
Introduction to EDA and Python coding
00:00Important Terminoogies in EDA
00:00Why and how to deal missing values?
00:00Missing Value Imputation in Python
00:00Complete A-Z EDA Project
00:00Automatic EDA
00:00AutoViz Library
00:00Use Ai for Fast paced EDA
00:00Big Datasets for EDA practice
00:00EDA on Apple Store Apps (Part-1)
00:00EDA on Apple Store Apps (Part-2)
00:00Complete EDA on Apple APP store Data
00:00
Web Application development and Deployment
Web application development is the process of creating web-based applications that can be accessed through the internet. It involves the development of a web browser-based interface that can be used to interact with a web server. Web application development involves the use of technologies such as HTML, CSS, JavaScript, and related frameworks. It can also involve the use of databases and other web technologies. Once the web application has been developed, it must be deployed on a web server, which is responsible for serving the application to users. Deployment involves the configuration of the web server, configuring the application, deploying the code on the server, and ensuring that the application is working properly. Web application deployment also involves security measures such as firewalls, encryption, and authentication. After deployment, the application must be maintained and monitored for any errors or performance issues.
Introduction to streamlit and your first web app
00:00Important logins for upcoming lectures
00:00Introduction to API
00:00Important APIs
00:00Apna chatGPT bnayen
00:00Introduction to LangChain
00:00Ask the text app (Complete Project)
00:00Ask the docx, pdf, txt file app- Advanced (Complete Project)
00:00Other important APIs for the app development
00:00Large Language Models (LLMs)
00:00
Machine Learning in desi style
Machine Learning in Desi Style is a way to learn the fundamentals of Machine Learning in a more fun and creative way. This involves using Indian languages and culture to help explain important concepts in Machine Learning. This style of learning can be useful for those who are new to the field as it can break down complex concepts into simpler terms. It can also be fun as it allows for students to explore their own cultural context when learning. The use of Indian languages can provide a unique perspective on the topics and allow students to gain insight into Machine Learning in a more personal way.
Introduction to Machine Learning
00:00Machine Learning and its types
00:00Regrssion vs. Classification and Types of Algorithms in Machine Learning
00:00Metrics of Regression Evaluation
00:00Missing values imputation for Data pre-processing (Part-1)
00:00Missing values imputation for Data pre-processing (Part-2)
00:00Simple- and Multi- Linear Regression
00:00Multiple Linear Regression and Types of Data Encoding
00:00Evaluating Regression Models – Must-Know Metrics Explained
00:00Regression vs. Classification
00:00Features vs Labels – Explaining the Core Machine Learning Data Components
00:00Sentiment Analysis Web App
00:00Evaluation Metrics for Classification models in Machine Learning
00:00Prompt Engineering to make a complete webapp in less than 13 minutes
00:00EDA using prompt engineering
00:00Classification Models in sk-learn (Logistic Regression)
00:00Regression vs. Classification
00:00Logistic Regression (Theory)
00:00Logistic Regression (Coding in Python)
00:00Evaluation Metrics for Classification
00:00Support vector Machines (Part-1)
00:00Support vector Machines (Part-2)
00:00Machine Learnig Types and algorithms defined in one liner
00:00Naive Bayes Algorithm
00:00Cross Validation
00:00K-Nearest Neighbours (KNN)
00:00Mathematics behind K-Nearest Neighbours Algorithm
00:00Best Model Selection out of many
00:00How to use github code?
00:00HyperParameter Tuning
00:00Selecting best Hyperparamter Tuned Model
00:00Pipelines in Machine Learning
00:00Ensemble Methods in Machine Learning ALgorithms
00:00Decision Tree Algorithm
00:00ADAboosting Algorithm
00:00Random Forest Algorithm`
00:00XGBoost, CATBoost, and lightGBM Algorithm
00:00Lasso and Ridge Regression | L1 and L2 Regularization
00:00Ensemble Algorithms in Python with coding
00:00Unsupervised Machine Learning Algorithms
00:00Clustering Algorithms
00:00K-means Clustering
00:00kmeans vs. kmeans++ Clustering
00:00Hierarchical Clustering Theory
00:00Hierarchical Clustering Practice in Python
00:00DBSCAN (Density-based spatial clustering of applications with noise)
00:00DBSCAN vs. OPTICS
00:00Gaussian Mixture Models (GMMs)
00:00Evaluation metrics for GMMs
00:00Feature Engineering (Part-1)
00:00Feature Engineering (Part-2)
00:00Principal Component Analysis (PCA) – (Part-1)
00:00Principal Component Analysis (PCA) – (Part-2)
00:00SVD (Singular Value Decomposition)
00:00tSNE (t-distributed Stochastic Neighbor Embedding)
00:00
Prompt Engineering
Prompt engineering is the process of designing and creating prompts for user-interfaces that help guide users to complete tasks. This process involves selecting appropriate prompts, designing the messages and the visuals associated with them, and also testing them to ensure they are effective. Prompt engineering is important because it allows developers to create user-interfaces that are intuitive and user-friendly. This helps users to quickly understand and complete tasks in an efficient manner.Prompt engineering often involves using best practices for designing effective prompts. This includes considering the user's context and goal, ensuring the language used is appropriate for the target audience, and making sure the visuals used are clear and understandable. Additionally, the process also involves testing the prompts with users to ensure they are effective and don't cause any confusion or frustration.Overall, prompt engineering is a critical part of UI design. It allows developers to create user-interfaces that are intuitive, user-friendly, and effective. It also helps to ensure that users are able to complete tasks in an efficient manner. Ultimately, prompt engineering can help to improve user experience and increase user satisfaction.
Prompt Engineering Crash course
00:00Using Prompt Engineering to Craft Powerful Prompts with AI
00:00Blogging Tips and Tricks using Prompt Engineering
00:00Website Development Using Hostinger AI prompting
00:00
What we have learned so far?
What we have learned so far?
00:00
Software Development
Develop Software to do EDA in Python
00:00
Online Earning
How to earn more using AI tools
00:00
Machine Learning one stop shop (Complete Project)
Full Stack ML in Python
00:00
How to use Google Colab?
Google Colab use, tips and tricks
00:00
Deep Learning in Desi Andaz
Deep Learning is a type of Artificial Intelligence (AI) that uses multiple layers of neural networks to learn from large amounts of data. It is capable of learning complex patterns and making decisions based on those patterns. Deep Learning models are trained by using large datasets that contain millions of data points. The models are then able to recognize patterns and make decisions or predictions about new data. Deep Learning is used in a variety of applications such as computer vision, natural language processing, and robotics. It is an important component of AI and has enabled computers to become more intelligent and perform tasks that were previously impossible.
Introduction to Deep Learning
00:00What is Neural Network? and How we can construct it
00:00Number of neurons in Each Layer
00:00Computer Vision (Basics)
00:00Deep Learning and Computer Vision
00:00Activation Functions (Part-1)
00:00Activation Functions (Part-2)
00:00Activation Functions (Part-3)
00:00How to choose an activation function?
00:00Artificial Neural Network (Basic Network Structure)
00:00ANN Advance Theory with Concepts
00:00Regression and call back function
00:00Binary and Multi-class classification
00:00Training and Validation loss
00:00Convulutional Neural Network (CNN)- (Part-1)
00:00Convolutional Neural Network (CNN) Theory -(Part-2)
00:00Convolutional Neural Network (CNN) Practice in Python-(Part-3)
00:00Master Convolutional Neural Network (CNN) – (Part-4)
00:00Recurrent Neural Network (RNN), LSTM and GRU in Python
00:00Recurrent Neural Network (RNN), Time Series and NLP
00:0015 Important Key terms for NLP and prompting
00:00
WebApp deployment
Important Logins and websites
00:00Web App development and Deployment using prompt engineering, chatGPT, github and streamlit cloud
00:00
All about git and gitHub
git, gitTools and gitHub
00:00
Revision workshop
Earn Online
How to earn Money online using AI and Data Science Skills?
00:00
FeedBack
Your Feedback Matters
00:00
Earn a certificate
Add this certificate to your resume to demonstrate your skills & increase your chances of getting noticed.
Student Ratings & Reviews
No Review Yet
