SIREN

SIREN on Beyond Market Intelligence: a running collection of 3 stories we have gathered and hand-picked because they are worth your time. Every post here touches on siren in some way — the news, the analysis, the deep dives, and the occasional surprise find. Acme AI is the next-generation, AI-powered spreadsheet platform built to replace Excel and redefine how analysts, data scientists, and enterprise teams work with data. New stories are added to this page as we find them, so check back if you want to keep up with what is happening around siren, or subscribe to the RSS feed to get them as soon as they are published. Browse the collection below, or head back to the homepage to see everything Beyond Market Intelligence is covering right now.

Machine Learning

How much of the weight-space perception gap is actually symmetry? Evidence from ~1.8M fitted SIRENs [R]

Recent research investigates the weight-space perception gap in AI, specifically exploring how much of the degradation in performance arises from parameter symmetry when neural networks are fitted independently. Analyzing nearly 1.8 million SIREN networks across benchmark datasets, the study demonstrates that randomizing the symmetry group alone accounts for a striking 79.1% of the accuracy loss observed when comparing shared-initialization versus independent initialization. This establishes the sufficiency of symmetry in reproducing much of this performance gap.

Machine Learning

Improved compression of Bad Apple into a Neural Network [P]

Recent experimentation with SIREN networks has yielded significant improvements in compressing the "Bad Apple" video. By employing a novel batch generation technique that incorporates pixels across the entire video, we’ve achieved a more faithful reproduction while maintaining the original model architecture—4 x 512 wide sine layers totaling 792,257 parameters. While a full framerate version proved challenging due to increased temporal data demands, the low-rate version demonstrates compelling compression capabilities. This reimplementation, built using GPT5.

Machine Learning

I Compressed Bad Apple into a 3MB Neural Network [P]

Researchers have achieved a remarkable feat: compressing the iconic "Bad Apple" animation—approximately 2.7 billion pixels—into a remarkably compact 3MB neural network. This MLP, utilizing 790,000 parameters and sine activations (SIREN), effectively memorizes the video by predicting grayscale values based on spatial and temporal coordinates. Through innovations like time-stretching and motion-focused sampling, the model demonstrably improved reconstruction quality, achieving a 9x reduction in validation MSE.