arXiv subjects

Mayukh Deb

Publications and source records attributed to Mayukh Deb.

4 recordsLinked to original sources

arXiv2025

Topographic Constraints Shape Brain-Like Component Structure in Auditory Models

If topography is a fundamental feature of the brain, it should influence both how neurons are arranged in space (i.e. explain brain maps) and how information is structured within the neural population. The human auditory cortex provides a strong, but previously underused test for the latter idea. Neural responses measured with both fMRI and ECoG can be decomposed into interpretable components corresponding to sound categories such as speech, music, and song, offering a view of how sound information is partitioned in the brain. Here we ask whether introducing topographic constraints into the training of audio neural network models shapes their internal representations to better match the component structure observed in the brain. To address this question, we introduce a new class of topographic auditory models, TopoAudio, which incorporate wiring-length constraints and encourage nearby units on a two-dimensional cortical sheet to develop similar response tuning. Despite these additional constraints we find that TopoAudio achieves comparable performance on standard speech and environmental sound classification tasks to standard non-topographic models and matches them in predicting human fMRI responses. Crucially however, topographic models develop more compact internal representations, and their inferred components align more closely with those derived from human ECoG recordings. These results provide initial evidence that topography offers a general mechanism for producing biologically aligned internal representations in artificial neural networks. More broadly, component-level alignment provides a complementary way for testing whether topography reshapes population responses in models to better match the representational structure observed in neural recordings. Our project page: https://topoaudio.github.io

q-bio.NC↗

arXiv2025

TopoNets: High Performing Vision and Language Models with Brain-Like Topography

Neurons in the brain are organized such that nearby cells tend to share similar functions. AI models lack this organization, and past efforts to introduce topography have often led to trade-offs between topography and task performance. In this work, we present TopoLoss, a new loss function that promotes spatially organized topographic representations in AI models without significantly sacrificing task performance. TopoLoss is highly adaptable and can be seamlessly integrated into the training of leading model architectures. We validate our method on both vision (ResNet-18, ResNet-50, ViT) and language models (GPT-Neo-125M, NanoGPT), collectively TopoNets. TopoNets are the highest-performing supervised topographic models to date, exhibiting brain-like properties such as localized feature processing, lower dimensionality, and increased efficiency. TopoNets also predict responses in the brain and replicate the key topographic signatures observed in the brain's visual and language cortices. Together, this work establishes a robust and generalizable framework for integrating topography into leading model architectures, advancing the development of high-performing models that more closely emulate the computational strategies of the human brain.

cs.LG↗

arXiv2023

AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation

Generative transformer models have become increasingly complex, with large numbers of parameters and the ability to process multiple input modalities. Current methods for explaining their predictions are resource-intensive. Most crucially, they require prohibitively large amounts of extra memory, since they rely on backpropagation which allocates almost twice as much GPU memory as the forward pass. This makes it difficult, if not impossible, to use them in production. We present AtMan that provides explanations of generative transformer models at almost no extra cost. Specifically, AtMan is a modality-agnostic perturbation method that manipulates the attention mechanisms of transformers to produce relevance maps for the input with respect to the output prediction. Instead of using backpropagation, AtMan applies a parallelizable token-based search method based on cosine similarity neighborhood in the embedding space. Our exhaustive experiments on text and image-text benchmarks demonstrate that AtMan outperforms current state-of-the-art gradient-based methods on several metrics while being computationally efficient. As such, AtMan is suitable for use in large model inference deployments.

cs.LG↗

arXiv2022

DORA: Exploring Outlier Representations in Deep Neural Networks

Deep Neural Networks (DNNs) excel at learning complex abstractions within their internal representations. However, the concepts they learn remain opaque, a problem that becomes particularly acute when models unintentionally learn spurious correlations. In this work, we present DORA (Data-agnOstic Representation Analysis), the first data-agnostic framework for analyzing the representational space of DNNs. Central to our framework is the proposed Extreme-Activation (EA) distance measure, which assesses similarities between representations by analyzing their activation patterns on data points that cause the highest level of activation. As spurious correlations often manifest in features of data that are anomalous to the desired task, such as watermarks or artifacts, we demonstrate that internal representations capable of detecting such artifactual concepts can be found by analyzing relationships within neural representations. We validate the EA metric quantitatively, demonstrating its effectiveness both in controlled scenarios and real-world applications. Finally, we provide practical examples from popular Computer Vision models to illustrate that representations identified as outliers using the EA metric often correspond to undesired and spurious concepts.

cs.LG↗