Imad Dabbura

Hard-Learned Lessons in Shipping Software (AI/ML) Projects

Notes on Learning

7 min

Why Having the Last Layer in a Neural Network as Raw Logits is Better Than Softmax

Understanding Forward and Reverse-mode Automatic Differentiation in Deep Learning

Designing ML Systems

Git Confident

Notes for Deep Learning Systems

Transformer Architecture Explained

Tokenization Strategies

LSTM Implementation

C Program Startup

Does C program really start at main

Airflow Part 8 - Best Practices

Airflow Part 7 - Triggering Workflows

Airflow Part 6 - Sharing Data Between Tasks

Airflow Part 5 - Dependencies Between Tasks

Airflow Part 4 - Task Context & Jinja Templating

Airflow Part 3 - DAG Scheduling

Airflow Part 2 - DAGs

Airflow Part 1 - What is Airflow?

Anomaly Detection

Conda Essentials

Enough background about Conda to be productive!

Gradient Descent Algorithm and Its Variants

Deep dive into gradient descent algorithm: Batch vs. Mini-batch vs. Stochastic.

K-means Clustering: Algorithm, Applications, Evaluation Methods, and Drawbacks

Deep dive into K-means algorithm to find subgroups within data.

15 min

Machine Learning

Data Science

Unsupervised Learning

Coding Neural Network Part 5 - Dropout

What is Dropout, its use, and how to implement it?

Coding Neural Network Part 4 - Regularization

What is regularization and how it helps NN generalizes better?

Coding Neural Network Part 3 - Parameters’ Initialization

The role of parameter initialization in training and different ways to initialize parameters.

Coding Neural Network Part 2 - Gradient Checking

How to check numerically if the implementation of backward propagation is correct?

Coding Neural Network Part 1 - Forward & Backward Propagation

What it takes to go from input to output? And how to compute the gradients?

Bandit Algorithms: epsilon-Greedy Algorithm

What is epsilon-Greedy Algorithm and how to use it in A/B testing?

Predicting Loan Repayment

Trying different modeling techniques to deal with imbalanced data, missing values, and ensemble models.

Character-Level Language Model

Predict the next character given the previous charecter and state.

Predicting Employee Turnover

Experimenting with different models on employee turnover data.

Posts

Categories

Hard-Learned Lessons in Shipping Software (AI/ML) Projects

Notes on Learning

Why Having the Last Layer in a Neural Network as Raw Logits is Better Than Softmax

Understanding Neural Network Pruning: A Comprehensive Guide

Coding GPT2/3 (124M) From Scratch

Byte-level Byte-Pair Encoding (BPE)

Ideas to Improve RAG Applications

A Deep Dive into Python’s Modules and Packages

Understanding Forward and Reverse-mode Automatic Differentiation in Deep Learning

Designing ML Systems

Git Confident

Notes for Deep Learning Systems

Transformer Architecture Explained

Tokenization Strategies

LSTM Implementation

C Program Startup

Airflow Part 8 - Best Practices

Airflow Part 7 - Triggering Workflows

Airflow Part 6 - Sharing Data Between Tasks

Airflow Part 5 - Dependencies Between Tasks

Airflow Part 4 - Task Context & Jinja Templating

Airflow Part 3 - DAG Scheduling

Airflow Part 2 - DAGs

Airflow Part 1 - What is Airflow?

Anomaly Detection

Conda Essentials

Gradient Descent Algorithm and Its Variants

K-means Clustering: Algorithm, Applications, Evaluation Methods, and Drawbacks

Coding Neural Network Part 5 - Dropout

Coding Neural Network Part 4 - Regularization

Coding Neural Network Part 3 - Parameters’ Initialization

Coding Neural Network Part 2 - Gradient Checking

Coding Neural Network Part 1 - Forward & Backward Propagation

Bandit Algorithms: epsilon-Greedy Algorithm

Predicting Loan Repayment

Character-Level Language Model

Predicting Employee Turnover