Multiple Inheritance Functionality via Strategy Pattern in Java
Decomposing first-sight multiple inheritance issues via composition over inheritance pattern, making use of the Strategy Pattern
More issues
Advanced Feature Attribution Techniques for Deep Learning Models
Getting a glimpse into the world of Explainable AI (XAI) on Deep Learning models. Explore various techniques built to shed light on predictions made by deep learning neural networks.
Introduction to Graph Neural Networks: The Message Passing Framework
Graph Neural Networks (GNNs) are at the forefront of modern machine learning, offering powerful tools for modelling complex systems and structures. In this blog post, we will explore the fundamentals of GNNs, their applications, and the underlying mathematical principles.
Artificial Neural Network Backpropagation
Learn how backpropagation works in neural networks, from derivatives and the chain rule to gradient descent and delta updates.
From Bayesian Priors to Weight Decay
Deriving via MAP estimation how Gaussian priors in the Bayesian Framework lead to the well known L₂ weight decay regularization.
Relating Bayesian Inference, Expected Risk Minimization and Maximum Likelihood Estimation
A birds-eye view on Bayesian Inference, Empirical Risk Minimization and Maximum Likelihood Estimation, relating the different concepts to find core similarities and differences.
An Overview on Matrix Factorization and Dimensionality Reduction
Matrix factorization is a key method in linear algebra with various applications in data analysis and machine learning. Techniques like SVD, PCA, and NMF simplify complex datasets, improve computational efficiency, and reveal hidden patterns.
Reducing Docker Image Size and Enhancing Build Efficiency
Optimizing Docker images boosts deployment speed and cuts costs. Often overlooked, this key step is essential for scalability. A checklist can keep you on track.
Enforcing Distributed Rate Limiting with Hazelcast and Bucket4j
Enforcing distributed rate limiting with Bucket4j & Hazelcast. Navigate distributed system complexities for consistent control across multiple instances.
The Transformer Architecture
Explore the Transformer architecture covering scaled dot-product attention, multi-head attention, and positional encodings. Learn how encoder-decoder, encoder-only (BERT), and decoder-only (GPT) models work for NLP, translation, and generative AI.