Sohan Poudel

Attractor-Basin Failure under Transient Perturbations and the Limits of Spectral Trajectory Summaries

We study how large transient inputs cause post-perturbation memory failure in small recurrent neural networks (RNNs), and whether spectral summaries of early hidden-state trajectories provide information beyond simpler time-domain descriptions. Mechanistically, each of three tanh...

A Question Worth Answering: What Would a Neural Network Preserve?

The report asks a simple but focused question: if a numerical mechanism attached to a trained neural network had to select exactly one component to preserve, what would it choose, and would that choice predict real functional consequences better than simple baselines? We ran an e...

A Question Worth Answering: What Would a Neural Network Preserve?

The report asks a simple but focused question: if a numerical mechanism attached to a trained neural network had to select exactly one component to preserve, what would it choose, and would that choice predict real functional consequences better than simple baselines? We ran an e...

COTP: Center-Out Temporal Prediction

This repository contains the experimental artifacts and results for Center-Out Temporal Prediction (COTP), a center-conditioned approach to temporal representation learning. The study investigates whether a model given only a window from the middle of a time series can learn a us...

COTP: Center-Out Temporal Prediction

This repository contains the experimental artifacts and results for Center-Out Temporal Prediction (COTP), a center-conditioned approach to temporal representation learning. The study investigates whether a model given only a window from the middle of a time series can learn a us...