My journey into the AI world.

Hi, everyone! :)

This is my little summary, about my journey to the #AI world

after working consistently for 6 months in this pandemic.

1.)  Python

'Introduction to Computer Science and Programming Using Python' of Mitx on edx

• In this, I learned A Notion of computation, The Python programming language, simple algorithms, testing and debugging, An informal introduction to algorithmic complexity, and Data structures.

'Using Databases with python'  by Charles Severance

• In this, I learned How to Create, Read, Update, and Delete operations to manage databases, the basics of Object-Oriented Python, Understand how data is stored across multiple tables in a database, and Utilized the Google Maps API to visualize data

'Capstone: Retrieving, Processing, and Visualizing Data with Python'  by Charles Severance 

• In this, I learned How to Make use of Unicode characters and strings, Understand the basics of building a search engine, How to select and process the data of your choice, How to create email data visualizations

2.)  Mathematics

'Probability- the Science of Uncertainty' of Mitx on edx

• In this, I learned The basic structure and elements of probabilistic models, Random variables, their distributions, means and variances, Probabilistic calculations, Inference methods, Laws of large numbers and their applications, and Random processes

'Fundamentals of Statistics'  of Mitx on edx

• In this, I learned Construct estimators using a method of moments and maximum likelihood and decide how to choose between them, Quantify uncertainty using confidence intervals and hypothesis testing. Choose between different models using the goodness of fit test, Make prediction using linear, nonlinear and generalized linear models, Perform dimension reduction using principal component analysis (PCA)

3.)  Machine Learning

 'Machine Learning'  by Andrew NG on standford

• In this, I learned Logistic Regression, Artificial Neural Network, Machine Learning (ML) Algorithms, Machine Learning

4.)  Deep Learning

'Deep Learning Specialization'  by Andrew NG on deeplearning.ai

Which has courses like 

• Neural Network:- backpropagation, ANN
• Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization:- Hyperparameter, Tensorflow, Hyperparameter Optimization
• Structuring Machine Learning Projects:- Inductive Transfer, Multi-Task Learning
•  Convolutional Neural Networks:- Facial Recognition System, Tensorflow, Convolutional Neural Network, Artificial Neural Network
• Sequence models:- Recurrent Neural Network, Long Short-Term Memory (ISTM)

5.)  Applied Data Science

'Applied Data Science with Python Specialization'

which has courses like

• Introduction to Data Science in Python:- Understand techniques such as lambdas and manipulating CSV files, Describe common Python functionality and features used for data science, Query DataFrame structures for cleaning and processing, Explain distributions, sampling, and t-tests
• Applied Plotting, Charting & Data Representation in Python:- Describe what makes a good or bad visualization, Understand best practices for creating basic charts, Identify the functions that are best for particular problems, Create a visualization using matplotlib
• Applied Machine Learning in Python:- Describe how machine learning is different than descriptive statistics, Create and evaluate data clusters, Explain different approaches for creating predictive models, Build features that meet analysis needs
• Applied Text Mining in Python:- Understand how text is handled in Python, Apply basic natural language processing methods, Write code that groups documents by topic, Describe the nltk framework for manipulating text
• Applied Social Network Analysis in Python:- Represent and manipulate networked data using the NetworkX library, Analyze the connectivity of a network, Measure the importance or centrality of a node in a network, Predict the evolution of networks over time

6.)  Hands On-

Neural-machine translation English-to-Polish, American sign language detection, Chance of admission in the college, Data scientist salary prediction, and many more posted on my GitHub

and still learning

I'll be forever grateful to the Urvish Patel who guided me to explore these paths.