Deconstructing the "Black Box" - Optimizing Sequence Models for Dynamical Systems
A rigorous ablation study deconstructing the "black box" of sequence modeling. We synthesized novel hybrid …...
Evaluation
Digital Restoration: Modernizing Rahman's 1964 Argon Simulation
A high-fidelity replication of foundational molecular dynamics using modern software engineering practices: caching, …...
Can You Hear the Shape of a Molecule? (Part Three)
Supervised learning reveals hidden eigenvalue patterns that clustering missed, testing k-NN and logistic regression on …
Can You Hear the Shape of a Molecule? (Part Two)
Clustering analysis reveals why Coulomb matrix eigenvalues struggle with larger alkanes, using Dunn Index and silhouette …
Sarcasm Detection with Transformers: A Cautionary Tale
Learn how dataset bias can lead to misleading results in NLP: a sarcasm detection model that actually learned to …
How Does Congress Actually Work? Data from 15K Bills
What happens to bills in Congress? Analyzing 15K+ bills from the 117th Congress to understand legislative patterns, …
Analytical Solution to Word2Vec Softmax & Corpus Bias Probing
Analytical derivation of Word2Vec's softmax objective factorization and a new framework for detecting semantic bias in …...
HyperNEAT: Scaling Neuroevolution with Geometric Patterns
How HyperNEAT uses indirect encoding and geometric patterns to evolve large-scale neural networks with biological …
QuAC: Question Answering in Context Dataset
Analysis of QuAC's conversational QA through student-teacher interactions, featuring 100K+ context-dependent questions …
Word Embeddings in NLP: An Introduction
Learn about word embeddings in NLP: from basic one-hot encoding to contextual models like ELMo. Guide with examples.