Personal Growth

• Transforming Business Problems into Machine Learning Solutions

  This post explores the process of identifying whether a business problem can be effectively solved using machine learning. It delves into key considerations, such as impact and cost, and provides g...

  Date: June 17, 2024
  Categories: Frame an ML Problem | High-Impact and Low-Cost



---

• In-Depth Guide to Cross Entropy Loss

  An exploration of how cross entropy loss functions, demonstrated through a practical example with a language model.

  Date: February 21, 2024
  Categories: cross-entropy-loss | language-model



---

• Attention Mechanism

  This post provides brief timeline of the development of attention mechanism and how is applied in LLMs

  Date: January 22, 2024
  Categories: attention mechanism | LLMs



---

• Step by Step to Build a Multi-Lingual Translation Language Model with Transformer

  This guide provides a step-by-step tutorial on constructing a translation model using the Transformer architecture. We will code the encoder and decoder, train the model, save checkpoints, and perf...

  Date: December 05, 2023
  Categories: multi-lingual | transformer



---

• Perceptron and kernalization

  A exploration of linear and non-linear decision boundaries in binary classification, focusing on the perceptron algorithm and the kernel trick for transforming non-linearly separable data into a hi...

  Date: December 05, 2023
  Categories: Classification | Perceptron & Kernalization



---

• Maximum Likelihood (MLE) vs Maximum A Posteriori (MAP)

  This post provides an in-depth look at the difference between Maximum Likelihood Estimation (MLE) and Maximum A Posteriori (MAP) Estimation using concrete examples

  Date: May 11, 2023
  Categories: MLE | MAP | Gaussian Distribution



---

• How Does BPE Tokenization Work

  Tokenization is the process of breaking down text into smaller units called tokens. In the context of the Byte Pair Encoding (BPE) algorithm, tokenization involves splitting words into subword unit...

  Date: March 23, 2023
  Categories: tokenization | BPE



---

• Dimensionality Reduction

  This post provides an in-depth explanation of Principal Component Analysis (PCA), a dimensionality reduction technique commonly used in data analysis.

  Date: March 10, 2023
  Categories: PCA | Dimension reduction



---

• Unsupervised Learning and Clustering

  This post provides an in-depth look at various regression techniques, including parametric and non-parametric regression, linear regression, Lasso and Ridge regression, logistic regression, and ker...

  Date: December 15, 2022
  Categories: k-means | Hierarchicall Clustering | Gaussian Mixture Models



---

• A Gentle Introduction to Regression

  This post provides an in-depth look at various regression techniques, including parametric and non-parametric regression, linear regression, Lasso and Ridge regression, logistic regression, and ker...

  Date: December 11, 2022
  Categories: Regression Techniques | Parametric & Non-parametric Methods | Statistical Modeling



---

• Nearest Neighbors & Decision Tree

  This post explores the concepts of Nearest Neighbors (k-NN) and Decision Tree algorithms, including their pros and cons, and how to measure uncertainty using Gini impurity and entropy. A detailed e...

  Date: November 09, 2022
  Categories: Nearnest Neighbors | Decision Tree



---

• Intro to Machine Learning

  Machine Learning is the study of making machines learn a concept without explicitly programming it. It involves building algorithms that can learn from input data to make predictions or find patter...

  Date: October 11, 2022
  Categories: Supervised Learning | Unsupervised Learning `1



---

• Comprehensive Guide to Random Variables

  It delves into the concepts of discrete and continuous random variables, joint distributions, independence, and conditional independence. It provides a thorough understanding of how these elements ...

  Date: September 01, 2022
  Categories: Discrete & Continuous variables



---