The paper introduces a learning algorithm for threshold Boolean networks (TBNs) that can infer networks with a specified set of fixed points. The method uses a custom differentiable loss function to enforce fixed point preservation, penalize spurious attractors, encourage binary outputs, and promote sparsity via L1 regularization. When applied to the FOS-GRN model of Arabidopsis thaliana, the algorithm perfectly reconstructed all 10 desired fixed points in 5 of 30 runs and on average recovered 8.53 ± 0.90 correct fixed points without any spurious attractors, outperforming standard approaches such as the Perceptron and Logistic Regression.
arXiv:2607. 23289v1 Announce Type: cross Abstract: Gene regulatory network modeling often requires balancing predictive accuracy and mechanistic interpretability.
arXiv:2602.17493v2 Announce Type: replace-cross Abstract: We develop a method for training neural networks on Boolean data in which the values at all nodes are strictly $\pm 1$, and the resulting mod...
The paper demonstrates that using a single activation function across all nodes in artificial neural networks imposes hard limits on evolutionary search, particularly for sparse evolved substrates. By evolving per-node activation functions from an 18-function palette, the authors show that oscillatory functions can solve parity problems at all tested scales, while monotonic functions fail beyond the simplest case. The study reveals that the choice of activation functions, beyond topology and weights, critically influences what evolutionary search can achieve, and that heterogeneous assignments discovered via indirect encoding are unlikely to be selected manually.
arXiv:2607. 20555v1 Announce Type: new Abstract: The lottery ticket hypothesis proposes that large random neural networks contain sparse subnetworks that can match the performance of dense models after comparable training.
BIRDNet is a neural network that mines Boolean implication relationships (BIRs) from tabular data and encodes them as a sparse, interpretable architecture where each hidden unit represents a mined rule connecting two features. The design yields a model that is at most 2/d of the weights active per layer and retains symbolic identities for each unit, allowing direct rule extraction without surrogate models. Experiments on six transcriptomic and proteomic datasets show BIRDNet achieves AUROC within 0.02 of the best dense baseline while using up to 95× fewer active parameters, and its first‑layer rules align with known biological signatures.
arXiv:2607. 07425v1 Announce Type: cross Abstract: Many biological processes are governed by complex dynamical mechanisms that remain incompletely understood despite increasing volumes of experimental data.
arXiv:2607. 15525v1 Announce Type: cross Abstract: Kolmogorov--Arnold Networks (KANs) replace fixed node activations with learned one-dimensional edge functions, offering an explicit interface for interpretation and a possible alternative to transformer feed-forward networks.
arXiv:2606. 23880v1 Announce Type: new Abstract: From climate teleconnections to gene regulation, modern time-series datasets encompass tens or hundreds of interacting variables, making causal discovery increasingly challenging.
arXiv:2606. 30444v1 Announce Type: cross Abstract: Neural networks are known to be susceptible to over-reliance on spurious correlations.
arXiv:2608. 13171v1 Announce Type: cross Abstract: To avoid missing important variables and their connections in networks, more and more variables are included in network analysis.
arXiv:2606. 23587v2 Announce Type: replace Abstract: Previous work has found a gap between the scale of neural networks that reliably learn Conway's Game of Life, and minimal networks capable of representing the classic cellular automaton with hard-coded parameter values.
Biologically-informed neural networks (BINNs) are a subclass of physics-informed neural networks tailored for learning partial differential equations in biological systems, where equations are nonlinear and data are sparse. The paper introduces a diagnostic workflow for selecting hyperparameters—network capacity, training epochs, and term stability—without requiring known ground-truth equations. By applying this workflow to synthetic systems, the authors show that validation loss tracks true error and provide practical guidelines and starting values for BINN hyperparameter tuning.