Kunal Kumar Pant | Searcharxiv

arXiv2026

ChaosProbe: A Neurochaotic Lens on Frozen Transformer Input-Embedding Spaces

Transformer models are most often understood through what they do: their benchmark performance, generation quality, or behavior on downstream tasks. Yet frozen transformer input-embedding spaces may also be examined through their responses to a controlled deterministic probe before contextual computation or task-specific adaptation. Guided by this response-based view, we introduce \emph{ChaosProbe}, a deterministic neurochaos-inspired method for constructing response-based fingerprints of frozen transformer input-embedding spaces. For each prompt-level embedding matrix, ChaosProbe applies a chaotic trajectory-based transformation and summarizes its Firing Rate and Entropy channel responses with complementary representation-level measures, producing a fixed-length signature for each model. In a bounded proof-of-concept study of $80$ neutral prompts and four pretrained models---GPT-2, DistilGPT2, BERT-base-uncased, and RoBERTa-base---Pearson correlation, Spearman correlation, and cosine similarity each recover all four same-family nearest-neighbor assignments and both expected mutual family pairs. Euclidean distance recovers three of the four assignments and one of the two mutual family pairs. Paired bootstrap resampling supports the stability of the Pearson and Spearman pairings over the observed prompt set, and signature-validity checks show that constant or collapsed responses do not dominate the reported fingerprints. These results provide a cohort-dependent proof of concept that deterministic neurochaotic response signatures can expose broad structure among frozen transformer input-embedding spaces.

cs.LG↗

arXiv2025

Advancing Forest Fires Classification using Neurochaos Learning

Forest fires are among the most dangerous and unpredictable natural disasters worldwide. Forest fire can be instigated by natural causes or by humans. They are devastating overall, and thus, many research efforts have been carried out to predict whether a fire can occur in an area given certain environmental variables. Many research works employ Machine Learning (ML) and Deep Learning (DL) models for classification; however, their accuracy is merely adequate and falls short of expectations. This limit arises because these models are unable to depict the underlying nonlinearity in nature and extensively rely on substantial training data, which is hard to obtain. We propose using Neurochaos Learning (NL), a chaos-based, brain-inspired learning algorithm for forest fire classification. Like our brains, NL needs less data to learn nonlinear patterns in the training data. It employs one-dimensional chaotic maps, namely the Generalized L\"uroth Series (GLS), as neurons. NL yields comparable performance with ML and DL models, sometimes even surpassing them, particularly in low-sample training regimes, and unlike deep neural networks, NL is interpretable as it preserves causal structures in the data. Random Heterogenous Neurochaos Learning (RHNL), a type of NL where different chaotic neurons are randomnly located to mimic the randomness and heterogeneity of human brain gives the best F1 score of 1.0 for the Algerian Forest Fires Dataset. Compared to other traditional ML classifiers considered, RHNL also gives high precision score of 0.90 for Canadian Forest Fires Dataset and 0.68 for Portugal Forest Fires Dataset. The results obtained from this work indicate that Neurochaos Learning (NL) architectures achieve better performance than conventional machine learning classifiers, highlighting their promise for developing more efficient and reliable forest fire detection systems.

cs.NE↗