Author name cluster

Nauman Ahad

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

TMLR Journal 2025 Journal Article

Time Series Domain Adaptation via Channel-Selective Representation Alignment

Nauman Ahad
Mark A. Davenport
Eva L Dyer

Building generalizable and robust multivariate time series models can be challenging for real-world settings that involve significant shifts between training and testing. Existing unsupervised domain adaptation methods often struggle with real world distribution shifts which are often much more severe in some channels than others. To overcome these obstacles, we introduce a novel method called Signal Selection and Screening via Sinkhorn alignment for Time Series domain Adaptation (SSSS-TSA). SSSS-TSA addresses channel-level variations by aligning both individual channel representations and selectively weighted combined channel representations. This dual alignment strategy based on channel selection not only ensures effective adaptation to new domains but also maintains robustness in scenarios with training and testing set shifts or when certain channels are absent or corrupted. We evaluate our method on several time-series classification benchmarks and find that it consistently improves performance over existing methods. These results demonstrate the importance of adaptively selecting and screening different channels to enable more effective alignment across domains.

PDF Details

NeurIPS Conference 2023 Conference Paper

Relax, it doesn’t matter how you get there: A new self-supervised approach for multi-timescale behavior analysis

Mehdi Azabou
Michael Mendelson
Nauman Ahad
Maks Sorokin
Shantanu Thakoor
Carolina Urzay
Eva Dyer

Unconstrained and natural behavior consists of dynamics that are complex and unpredictable, especially when trying to predict what will happen multiple steps into the future. While some success has been found in building representations of animal behavior under constrained or simplified task-based conditions, many of these models cannot be applied to free and naturalistic settings where behavior becomes increasingly hard to model. In this work, we develop a multi-task representation learning model for animal behavior that combines two novel components: (i) an action-prediction objective that aims to predict the distribution of actions over future timesteps, and (ii) a multi-scale architecture that builds separate latent spaces to accommodate short- and long-term dynamics. After demonstrating the ability of the method to build representations of both local and global dynamics in robots in varying environments and terrains, we apply our method to the MABe 2022 Multi-Agent Behavior challenge, where our model ranks first overall on both mice and fly benchmarks. In all of these cases, we show that our model can build representations that capture the many different factors that drive behavior and solve a wide range of downstream tasks.

PDF Details

NeurIPS Conference 2022 Conference Paper

MTNeuro: A Benchmark for Evaluating Representations of Brain Structure Across Multiple Levels of Abstraction

Jorge Quesada
Lakshmi Sathidevi
Ran Liu
Nauman Ahad
Joy Jackson
Mehdi Azabou
Jingyun Xiao
Christopher Liding

There are multiple scales of abstraction from which we can describe the same image, depending on whether we are focusing on fine-grained details or a more global attribute of the image. In brain mapping, learning to automatically parse images to build representations of both small-scale features (e. g. , the presence of cells or blood vessels) and global properties of an image (e. g. , which brain region the image comes from) is a crucial and open challenge. However, most existing datasets and benchmarks for neuroanatomy consider only a single downstream task at a time. To bridge this gap, we introduce a new dataset, annotations, and multiple downstream tasks that provide diverse ways to readout information about brain structure and architecture from the same image. Our multi-task neuroimaging benchmark (MTNeuro) is built on volumetric, micrometer-resolution X-ray microtomography images spanning a large thalamocortical section of mouse brain, encompassing multiple cortical and subcortical regions. We generated a number of different prediction challenges and evaluated several supervised and self-supervised models for brain-region prediction and pixel-level semantic segmentation of microstructures. Our experiments not only highlight the rich heterogeneity of this dataset, but also provide insights into how self-supervised approaches can be used to learn representations that capture multiple attributes of a single image and perform well on a variety of downstream tasks. Datasets, code, and pre-trained baseline models are provided at: https: //mtneuro. github. io/.

PDF Details

NeurIPS Conference 2021 Conference Paper

Deep inference of latent dynamics with spatio-temporal super-resolution using selective backpropagation through time

Feng Zhu
Andrew Sedler
Harrison A Grier
Nauman Ahad
Mark Davenport
Matthew Kaufman
Andrea Giovannucci
Chethan Pandarinath

Modern neural interfaces allow access to the activity of up to a million neurons within brain circuits. However, bandwidth limits often create a trade-off between greater spatial sampling (more channels or pixels) and the temporal frequency of sampling. Here we demonstrate that it is possible to obtain spatio-temporal super-resolution in neuronal time series by exploiting relationships among neurons, embedded in latent low-dimensional population dynamics. Our novel neural network training strategy, selective backpropagation through time (SBTT), enables learning of deep generative models of latent dynamics from data in which the set of observed variables changes at each time step. The resulting models are able to infer activity for missing samples by combining observations with learned latent dynamics. We test SBTT applied to sequential autoencoders and demonstrate more efficient and higher-fidelity characterization of neural population dynamics in electrophysiological and calcium imaging data. In electrophysiology, SBTT enables accurate inference of neuronal population dynamics with lower interface bandwidths, providing an avenue to significant power savings for implanted neuroelectronic interfaces. In applications to two-photon calcium imaging, SBTT accurately uncovers high-frequency temporal structure underlying neural population activity, substantially outperforming the current state-of-the-art. Finally, we demonstrate that performance could be further improved by using limited, high-bandwidth sampling to pretrain dynamics models, and then using SBTT to adapt these models for sparsely-sampled data.

PDF Details

AAAI Conference 2021 Conference Paper

Semi-supervised Sequence Classification through Change Point Detection

Nauman Ahad
Mark A. Davenport

Sequential sensor data is generated in a wide variety of realworld applications. A fundamental machine learning challenge involves learning effective classifiers for such sequential data. While deep learning has led to impressive performance gains in recent years within domains such as speech, this has relied on the availability of large datasets of sequences with high-quality labels. In many applications, however, the associated class labels are often extremely limited, with precise labelling/segmentation being too expensive to perform in a high volume. However, large amounts of unlabeled data may still be available. In this paper we propose a novel framework for semi-supervised learning in such contexts. In an unsupervised manner, change point detection methods can be used to identify instances where classes change within a sequence. We show that change points provide examples of similar/dissimilar pairs of sequences which, when coupled with class labels, can be used in a semisupervised classification setting. Pairs from labels and change points are used by a neural network to learn improved representations for classification. We provide extensive synthetic simulations and show that the learned representations are better than those learned through an autoencoder and obtain improved results on simulations and human activity recognition datasets.

PDF Details