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 …
Blog Posts - Page 2
Technical articles on machine learning, computational chemistry, and scientific computing with deep dives into methodologies and practical implementations.
Can You Hear the Shape of a Molecule?
Explore molecular shape recognition using Coulomb matrix eigenvalues. Analysis of alkane isomers from data generation to …
Classifying Congressional Bills with Machine Learning
Testing ML classification of congressional bills by policy area. Comparing Naive Bayes, Logistic Regression, and XGBoost …
Coulomb Matrices for Molecular Machine Learning
Learn how Coulomb matrices encode 3D molecular structure for machine learning from basic theory to Python implementation …
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, …
Kabsch Algorithm: NumPy, PyTorch, TensorFlow, and JAX
Learn about the Kabsch algorithm for optimal point alignment with implementations in NumPy, PyTorch, TensorFlow, and JAX …
LAMMPS Tutorial: Copper Adatom Diffusion Simulation
LAMMPS tutorial for copper surface diffusion simulation and ML training data generation. Includes setup, analysis, and …
Platinum Adatom Diffusion on Pt(100) Surface
LAMMPS tutorial for platinum adatom diffusion simulation and ML training data. Learn how heavier atoms behave …
Generating Mini-Protein Trajectories with GROMACS
Systematic GROMACS workflows for simulating mini-proteins across multiple amino acids to generate diverse MD …
5 Axes of Multi-Arm Bandit Problems
A decomposition of multi-arm bandit problems into five key dimensions to help practitioners navigate the …
HyperNEAT: Scaling Neuroevolution with Geometric Patterns
How HyperNEAT uses indirect encoding and geometric patterns to evolve large-scale neural networks with biological …
NEAT: Evolving Neural Network Topologies
Learn about NEAT's approach to evolving neural networks: automatic topology design, historical markings, and speciation …