JPC: Flexible Inference for Predictive Coding Networks in JAX
We introduce JPC, a JAX library for training neural networks with Predictive Coding. JPC provides a simple, fast and flexible interface to train a variety of PC networks (PCNs) including discriminative, generative and hybrid models. Unlike existing libraries, JPC leverages ordinary differential equation solvers to integrate the gradient flow inference dynamics of PCNs. We find that a second-order solver achieves significantly faster runtimes compared to standard Euler integration, with comparable performance on a range of tasks and network depths. JPC also provides some theoretical tools that can be used to study PCNs. We hope that JPC will facilitate future research of PC. The code is available at https://github.com/thebuckleylab/jpc.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Divide-and-Conquer Predictive Coding: a structured Bayesian inference algorithm
Unexpected stimuli induce "error" or "surprise" signals in the brain. The theory of predictive coding promises to explain these observations in terms of Bayesian inference by suggesting that the cortex implements variati…
Bayesian InferenceVariational InferenceA Deep Generative Model Imitating Predictive Coding in Human Brain
In recent years, the development of deep generative models for prediction has been attracting attention. In our study, we focus on predictive coding, a concept from the neuroscience literature that hypothesizes the brain…
PredictionPrediction IntervalsPredictive Coding beyond Correlations
Recently, there has been extensive research on the capabilities of biologically plausible algorithms. In this work, we show how one of such algorithms, called predictive coding, is able to perform causal inference tasks.…
Bayesian InferenceCausal DiscoveryCausal Inferencecounterfactual+3Dystruct: Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference
Diffusion language models (DLMs) have recently emerged as a promising alternative to autoregressive models, primarily due to their ability to enable parallel decoding. Despite this advantage, most existing DLMs rely on a…
Bayesian InferenceText GenerationHybrid Predictive Coding: Inferring, Fast and Slow
Predictive coding is an influential model of cortical neural activity. It proposes that perceptual beliefs are furnished by sequentially minimising "prediction errors" - the differences between predicted and observed dat…
Bayesian InferenceObject Recognition