/ML-stack

Full Stack Machine Learning

Primary LanguageJupyter Notebook

Python

Python Concepts

  1. Basics Topics
    • Datatypes
    • If else
    • for loop
    • while loop
    • functions
    • input and output
    • operators
  2. Algorithms
    • Sorting
    • Searching
    • Brute Force
    • Recursive
    • BackTracking
    • Dynamic programming
    • Greedy
    • Hashing
    • Divide and conquer
  3. Data Structures
    • Strings
    • List
    • Tuple
    • Dictionary
    • Set
  4. Intermediate Data Structure
    • Stack
    • Queue
    • Linked List
    • Heap
    • Trees
    • Graphs
    • Hashing
    • Matrix
  5. Advanced Data Structure
    • Trie
    • Segment Tree
    • Set
  6. Intermediate Python Topics
    • CLI
    • Keyword Arguments
    • iterators
    • lambda function
    • Classes and objects
    • __init__
    • access specifier
  7. Object Oriented Programming
    • Inheritance
    • Polymorphism
    • Abstraction
    • Encapsulation
    • Constructors and destructures
    • Overloading
    • Overriding
  8. Advanced Python Topics
    • File Handling
    • Meta Class
    • Decorators
    • Exception handling
    • Collections
    • Generator
    • itertools
    • magic methods
    • Regular Expression
    • Threading
  9. Testing
    • Pytest
  10. Other Libraries
    • os
    • urllib
    • requests

Frameworks

  1. Flask
  2. FastAPI
  3. Django
  4. StreamLit
  5. Langchain

Machine Learning Stack

Maths

  1. Linear Algebra
  2. Trigonometry
  3. Calculus
  4. Statistics
  5. Probability

Databases

  1. SQL
    • MySQL
    • Postgres
    • SQLite
  2. NoSQL
    • MongoDB
  3. Vector Databases

Data Manipulation and Visualization

  1. Numpy
  2. Pandas
  3. Matplotlib
  4. Plotty

WebScraping and Automation

  1. Beautiful Soup
  2. Scrapy
  3. Selenium

Machine Learning Frameworks

  1. Scikit-learn
  2. NLTK
  3. Spacy
  4. Scipy

Machine Learning Basics

  1. Regularization
  2. Loss Functions
  3. Metrics
  4. Optimizers

Supervised Machine Learning

Classification

  1. Logistic Regression
  2. Naive Bayes
  3. Support Vector Machine
  4. Decision Trees
  5. Random Forest
  6. XGBoost
  7. CatBoost

Regression

  1. Linear Regression
  2. Polynomial Regression
  3. Ridge Regression

Unsupervised Machine Learning

Clustering

  1. K-Means
  2. Hierarchical

Association

  1. Apriori

Deep Learning Frameworks

  1. Tensorflow
  2. PyTorch
  3. Jax

Computer Vision

Basics

  1. Regularization
  2. Loss Functions
  3. Metrics
  4. Optimizers

Advanced

  1. Neural Networks
  2. Hyperparameter Tuning
  3. Convolution Neural Network

Deep Learning

  1. Image Classification
    • CNN and SOTA architectures
  2. Image Segmentation
    • Semantic Segmentation
    • Instance Segmenation
  3. Object Detection
    • Object Recognition
    • Object Localization
    • Object Detection
  4. Video

Generative Networks

  1. GANs
  2. AutoEncoders
  3. StableDiffusion

Transformers

  1. Vision Transformers

NLP Stack

NLP Basics

  1. Text Preprocessing
  2. Stopwords
  3. Tokenization
  4. Stemming
  5. Lemmatization
  6. Parts of Speech Tagging
  7. Dependency Parsing
  8. Embedding

Deep Learning Models

  1. Sequence Models

  2. PyTorch

  3. Tensorflow

  4. NLP Advanced

Transformers

  1. Attention is all you need
  2. Sequence to Sequence Encoder-Decoder Models (Text 2 Text)
  3. Encoder-Only Models Auto Encoding Models (Masked Language Modelling)
  4. Decoder-Only Models Auto-Regressive Models (Causal Language Modelling)
  5. Language Models

Large Language Models and Generative AI

  1. LLM and Gen AI

Prompt Engineering

Audio

  1. Automatic Speech Recognition
    • Speech to text
    • Text to Speech
  2. Audio Segmentation
  3. Audio Classification
  4. Audio to Audio

MultiModal

  1. Text to Image
  2. Image to Text
  3. Audio to Text
  4. Text to Audio
  5. Text to Video
  6. Video to Text

Time Series

Deep Learning Models

  1. ARIMA
  2. LSTM

MLOps

Frameworks

  • MLFlow
  • KubeFlow

Docker

Kubernetes

Papers