Software Engineer
Explorations in Machine Learning and Computer Vision
This post outlines the internal architecture behind Briefly©, an open-source, LLM-powered investment assistant. It focuses on MCP, portfolio- and news-grounded RAG, and context memory.
This project is an experiment in orchestrating tool-based reasoning using large language models (LLMs). The goal was to create a minimal, extensible investment advisor that can provide portfolio-specific guidance using real-time data.
Training the ESRGAN is not a straight forward process and will invoke knowledge from various concepts about deep learning and generative adversarial networks to understand.
The generator's architecture in an ESRGAN takes a low resolution image and outputs a higher resolution image through convolutions, activations, concatenation and addition of feature maps.
The ESRGAN is a neural network that uses convolutions to learn to create higher resolution images of a lower resolution image using generator and discriminator architectures.
Before delving into backpropagation, intuition is required first about the forward pass through a neural network. This article covers both deep neural networks and convolutional neural networks.
A neural network is a network of transformations that input data goes through to yield a desired output. This article explores how convolutions work in image processing.
A digital image is fundamentally comprised of slates called channels, each of which represent a color. When these channels are stacked, they create a wonderfully-colored image.
Understanding 3D textures and channel information. Images used as textures for 3D models are often referred to as 3D textures, mapped to 3D surfaces through UV mapping.