Index

Aritra Bandyopadhyay

[ DEPT. OF MACHINE LEARNING ]

RECORD No. 042:
Exploring mechanistic interpretability, multimodal systems, and information retrieval. This Quarto template provides a typewriter-inspired layout, recalling classical academic manuscripts and archival records.

READ.NOTES VIEW.PUBS OPEN.CV

GITHUB LINKEDIN SCHOLAR EMAIL

RESEARCH.FOCUS

I’m fascinated by the internal structure of language models, practical information retrieval, and medical-facing computer vision systems. This setup avoids Quarto’s rigid built-in about templates in favor of a flexible layout.

FILE: 01-FOCUS

INTERPRETABILITY

Mechanistic interpretability, post-training behavior, and making neural representations transparent.

FILE: 02-ENG

ENGINEERING

Bridging the gap between research fellowships, startup ML engineering, and reliable deployment.

FILE: 03-EXP

FRAMEWORKS

Maintaining content parity across Quarto, Astro, Jekyll, and Hugo to find the perfect stack.

FEATURED.PUBLICATION

[Differential Evolution Algorithm Based Hyper-Parameter Selection of CNNs for Speech Command Recognition]

VENUE: IJCCI / ECTA | YEAR: 2023

An evolutionary hyper-parameter search paper exploring the optimal architecture for convolutional neural networks in audio processing.

READ.PAPER

OPEN.SOURCE.REPOS

PANDAS

REPO ↗

Flexible and powerful data analysis and manipulation library for Python.

PYTORCH

REPO ↗

The deep learning stack that keeps showing up in research code and production prototypes.