Structure and parameter domain of motifs For the investigated three motif types, as Fig. 1a shows, each…
Continue ReadingTag: neural
Deep convolutional and fully-connected DNA neural networks
Working principles Herein, we have established a Classified allosteric-toehold based continuous and ultra-accurate (CALCUL) computing unit…
Continue Reading
Efficient event-based delay learning in spiking neural networks
Theory Learning weights in networks with delay We start by defining our two differential equations in…
Continue Reading
Bayesian continual learning and forgetting in neural networks
Description of the variational inference framework Exact computation of the truncated posterior (Eq. (4)) becomes intractable…
Continue Reading
Unifying machine learning and interpolation theory via interpolating neural networks
Discretization of the input domain Consider a regression problem that relates I inputs and L outputs.…
Continue Reading
Explosive neural networks via higher-order interactions in curved statistical manifolds
High-order interactions in curved manifolds The maximum entropy principle (MEP) is a general modelling framework based…
Continue Reading
Detecting genetic interactions with visible neural networks
To showcase the potential of our approaches in real-life data, we applied the methods to the…
Continue Reading
Uncertainty quantification with graph neural networks for efficient molecular design
Molecular design benchmarks To effectively evaluate molecular design strategies, tasks must be complex enough to reflect…
Continue Reading
CodonTransformer: a multispecies codon optimizer using context-aware neural networks
Data A total of 1,001,197 DNA sequences were collected from NCBI resources from 164 organisms including…
Continue Reading
Trainable Communication Systems Based on the Binary Neural Network
1 Introduction An autoencoder-based communication system regards the entire physical layer, i.e., “transmitter-channel-receiver,” as an end-to-end…
Continue Reading