In this collection of articles I’m trying to answer some of the questions that arise in doing science, math and programming.
Use the search to find a topic across the whole site.
- La mente che conta fino a dieci
- A controlled testbed for Repeat-Your-Self — SAT solving, message passing, and a predictive rho/phi theory
- Deep Equilibrium Models as a model for RYS
- Fractal Connectivity Scaffold Networks
- Multiscale structured recurrence with fractal connectivity networks
- Hippocampal scaffold networks
- Similarity of neural networks representations
- Functional synthetic LLM connectome analysis
- How skip connections define graphs in deep networks
- PLP Inference Audited Against Murphy
- The Master Equation of a Messy World
- Amortized structural variational inference for probabilistic language programming
- Kolmogorov-Arnold theorem, KANs, and the `eml` operator
- The continuous Sheffer stroke is all you need
- Interpretations for the Kullback-Leibler divergence, or relative entropy
- From hard to soft operators: between machine learning and statistical physics
- Latent traces and Landau free energy
- Latent traces and Landau free energy
- Statistical mechanics of decision making
- Chain-of-thought as grand-canonical inference in energy-based language models
- Latent traces and Landau free energy
- Random rooted trees, continuation free energy, and the Diligent Learner
- MellowMax, Doob's h-transform, and the intensive geometry of tool-use agents
- Recursive decomposition with a continuation policy
- Short-prefix soft values: a null result
- Soft values, symmetry breaking, and random rooted trees
- Inference-Time Steering as a Discrete Schrödinger Bridge
- PLP is inference-time approximation of free energy
- Test-time inference, language models and energy based models
- Scaffolding Is All You Need
- Probabilistic Language Programming, turning craft into solid science
- Intelligenza Artificial Neurosimbolica
- Introducing skfolio new online convex optimization module
- Hard and soft analogies in machine learning
- Configuration-model Surprise for community detection
- Multilabel classification with Parabel and efficient at-k metrics
- The Woodbury matrix identity
- Prefixspan algorithm for frequent subsequences visualization
- Eigenvectors from eigenvalues a numpy implementation
- Sampling uniform spanning forests with Wilson algorithm in Python
- The link between machine learning and statistical physics
- Quantum statistical mechanics of complex networks in networkqit
- Hidden Markov Models or HMM
- Short introduction to measure theory
- Low rank estimation of sparse observed ratios
- Smooth approximation to the floor function
- Einstein summation in Numpy
- Showing brain parcellation in Python with nilearn and some hacking
- Weighted graphs from adjacency matrix in graph-tool
- Random matrix ensemble spectral density and the average resolvent
- Some considerations about the spectral entropies framework
- Why probabilistic programming matters
- Dataset of biologically derived graphs
- An identity for zero
- Inequalities, traces, densities, matrices
- Distance matrix of the air500 complex network
- Lambda functions composition in Python 3
- The Enhanced weighted random graph model (EWRG)
- Plugging the weighted random graph into Surprise
- Statistical mechanics of networks - Park and Newman model of hidden variables
- Eigenvalue spectra of modular matrix techniques and calculations
- Computing Euler angles from 3x3 rotation matrix in Matlab
- Computing hypergeometric probability efficiently in C++
- Comparing spectral densities of random graph models.
- Detecting the consensus communities in graphs