Hopfield Networks Meet Big Data: A Brain-Inspired Deep Learning Framework for Semantic Data Linking

The exponential rise in data generation has led to vast, heterogeneous datasets crucial for predictive analytics and decision-making. Ensuring data quality and semantic integrity remains a challenge. This paper presents a brain-inspired distributed cognitive framework that integrates deep learning with Hopfield networks to identify and link semantically related attributes across datasets. Modeled on the dual-hemisphere functionality of the human brain, the right hemisphere assimilates new information while the left retrieves learned representations for association. Our architecture, implemented on MapReduce with Hadoop Distributed File System (HDFS), leverages deep Hopfield networks as an associative memory mechanism to enhance recall of frequently co-occurring attributes and dynamically adjust relationships based on evolving data patterns. Experiments show that associative imprints in Hopfield memory are reinforced over time, ensuring linked datasets remain contextually meaningful and improving data disambiguation and integration accuracy. Our results indicate that combining deep Hopfield networks with distributed cognitive processing offers a scalable, biologically inspired approach to managing complex data relationships in large-scale environments.

Unsupervised Spiking Neural Network Model of Prefrontal Cortex to study Task Switching with Synaptic deficiency

In this study, we build a computational model of Prefrontal Cortex (PFC) using Spiking Neural Networks (SNN) to understand how neurons adapt and respond to tasks switched under short and longer duration of stimulus changes. We also explore behavioral deficits arising out of the PFC lesions by simulating lesioned states in our Spiking architecture model. Although there are some computational models of the PFC, SNN's have not been used to model them. In this study, we use SNN's having parameters close to biologically plausible values and train the model using unsupervised Spike Timing Dependent Plasticity (STDP) learning rule. Our model is based on connectionist architectures and exhibits neural phenomena like sustained activity which helps in generating short-term or working memory. We use these features to simulate lesions by deactivating synaptic pathways and record the weight adjustments of learned patterns and capture the accuracy of learning tasks in such conditions. All our experiments are trained and recorded using a real-world Fashion MNIST (FMNIST) dataset and through this work, we bridge the gap between bio-realistic models and those that perform well in pattern recognition tasks