Researchers Propose Error-Driven Predictive Learning as Framework for How Neocortex Learns
Researchers have introduced error-based predictive coding (ePC), a reparameterization of the brain-inspired predictive coding (PC) learning algorithm that eliminates a fundamental signal decay problem plaguing its predecessor. The original state-based PC formulation was shown to suffer from exponential signal decay in digital simulation, making it computationally expensive and unable to scale to deep architectures. The work, accepted at ICML 2026, establishes a practical path for scaling PC-based learning to deeper neural networks on standard digital hardware.
Predictive coding (PC) is a neuroscience-inspired alternative to backpropagation for training neural networks, framed as a physical system minimizing internal energy. However, the canonical state-based formulation (sPC) has long struggled in digital simulation due to excessive compute demands and poor scalability to deeper models. The paper's authors identify the root cause as an inherent exponential signal decay in sPC that stalls the minimization process. To address this, they introduce error-based PC (ePC), a novel reparameterization that avoids signal decay and computes exact PC weight gradients orders of magnitude faster than sPC. Experiments across multiple architectures and datasets show ePC matches backpropagation's performance even on deeper models where sPC fails. The authors acknowledge that ePC sacrifices biological plausibility in exchange for computational efficiency. The work also provides new theoretical insight into PC dynamics and is positioned as a foundation for future scaling of PC-based learning on digital and potentially neuromorphic hardware.
What's missing
The paper does not address whether ePC retains any of the potential hardware advantages (e.g., on neuromorphic chips) that originally motivated PC research. The scope of 'deeper architectures' tested is not specified in the abstract, leaving open questions about performance on very large-scale models such as large language models.
What different sources said
- arXiv cs.AICenter
ePC: Fast and Deep Predictive Coding in Digital Simulation
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.