BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Srinandan Dasmahapatra

Srinandan Dasmahapatra appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Computer VisionBiological PhysicsMachine LearningMolecular NetworksApplicationsArtificial Intelligencehep-phhep-thPopulations and EvolutionQuantitative MethodsSystems and Control

Catalog footprint

What is connected

11works
11topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

11 published item(s)

preprint2026arXiv

Mini-Batch Class Composition Bias in Link Prediction

Prior work on node classification has shown that Graph Neural Networks (GNNs) can learn representations that transfer across graphs, when underlying graph properties are shared. For a fixed graph, one would then expect GNNs trained for link prediction to learn a representation consistent with that learnt for node classification. We show this intuition does not hold in the general case. Instead, we find popular link prediction models can learn a trivial mini-batch dependent heuristic, enabled by batch-normalisation layers, to solve the edge classification task. When correcting for this, we observe increased alignment of the network representation with node-class relevant features, suggesting the network has learnt a graph representation that better aligns with the underlying graph's properties. Our findings suggest that standard link prediction training may be leading us to overestimate link predictors' ability to learn a generalised representation of a graph that is consistent across tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Understanding Imbalanced Forgetting in Rehearsal-Based Class-Incremental Learning

Neural networks suffer from catastrophic forgetting in class-incremental learning (CIL) settings. Rehearsal$\unicode{x2013}$replaying a subset of past samples$\unicode{x2013}$is a well-established mitigation strategy. However, recent results suggest that, despite balanced rehearsal allocation, some classes are forgotten substantially more than others. Despite its relevance, this imbalanced forgetting phenomenon remains underexplored. This work shows that imbalanced forgetting arises systematically and severely in rehearsal-based CIL and investigates it extensively. Specifically, we construct, from a principled analysis, three last-layer coefficients that capture different gradient-level sources of interference affecting each past class during an incremental step. We then demonstrate that, together, they reliably predict how past classes will rank in terms of forgetting at the end of that step. While predictive performance alone does not establish causality, these results support the interpretation of the coefficients as a plausible mechanistic account linking last-layer gradient-level interactions during training to class-level forgetting outcomes. Notably, one coefficient$\unicode{x2013}$capturing self-induced interference$\unicode{x2013}$emerges as the strongest predictor, with controlled experiments providing evidence consistent with this coefficient being influenced by the new-class interference coefficient. Overall, our findings provide valuable insights and suggest promising directions for mitigating imbalanced forgetting by reducing class-wise disparities in the identified sources of interference.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

"Teaching Independent Parts Separately" (TIPSy-GAN) : Improving Accuracy and Stability in Unsupervised Adversarial 2D to 3D Pose Estimation

We present TIPSy-GAN, a new approach to improve the accuracy and stability in unsupervised adversarial 2D to 3D human pose estimation. In our work we demonstrate that the human kinematic skeleton should not be assumed as a single spatially codependent structure; in fact, we posit when a full 2D pose is provided during training, there is an inherent bias learned where the 3D coordinate of a keypoint is spatially codependent on the 2D coordinates of all other keypoints. To investigate our hypothesis we follow previous adversarial approaches but train two generators on spatially independent parts of the kinematic skeleton, the torso and the legs. We find that improving the self-consistency cycle is key to lowering the evaluation error and therefore introduce new consistency constraints during training. A TIPSy model is produced via knowledge distillation from these generators which can predict the 3D ordinates for the entire 2D pose with improved results. Furthermore, we address an unanswered question in prior work of how long to train in a truly unsupervised scenario. We show that for two independent generators training adversarially has improved stability than that of a solo generator which collapses. TIPSy decreases the average error by 17\% when compared to that of a baseline solo generator on the Human3.6M dataset. TIPSy improves upon other unsupervised approaches while also performing strongly against supervised and weakly-supervised approaches during evaluation on both the Human3.6M and MPI-INF-3DHP datasets.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Optimising 2D Pose Representation: Improve Accuracy, Stability and Generalisability Within Unsupervised 2D-3D Human Pose Estimation

This paper addresses the problem of 2D pose representation during unsupervised 2D to 3D pose lifting to improve the accuracy, stability and generalisability of 3D human pose estimation (HPE) models. All unsupervised 2D-3D HPE approaches provide the entire 2D kinematic skeleton to a model during training. We argue that this is sub-optimal and disruptive as long-range correlations are induced between independent 2D key points and predicted 3D ordinates during training. To this end, we conduct the following study. With a maximum architecture capacity of 6 residual blocks, we evaluate the performance of 5 models which each represent a 2D pose differently during the adversarial unsupervised 2D-3D HPE process. Additionally, we show the correlations between 2D key points which are learned during the training process, highlighting the unintuitive correlations induced when an entire 2D pose is provided to a lifting model. Our results show that the most optimal representation of a 2D pose is that of two independent segments, the torso and legs, with no shared features between each lifting network. This approach decreased the average error by 20\% on the Human3.6M dataset when compared to a model with a near identical parameter count trained on the entire 2D kinematic skeleton. Furthermore, due to the complex nature of adversarial learning, we show how this representation can also improve convergence during training allowing for an optimum result to be obtained more often.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Revisiting Jet Clustering Algorithms for New Higgs Boson Searches in Hadronic Final States

We assess the performance of different jet-clustering algorithms, in the presence of different resolution parameters and reconstruction procedures, in resolving fully hadronic final states emerging from the chain decay of the discovered Higgs boson into pairs of new identical Higgs states, the latter in turn decaying into bottom-antibottom quark pairs. We show that, at the Large Hadron Collider (LHC), both the efficiency of selecting the multi-jet final state and the ability to reconstruct from it the masses of the Higgs bosons (potentially) present in an event sample depend strongly on the choice of acceptance cuts, jet-clustering algorithm as well as its settings. Hence, we indicate the optimal choice of the latter for the purpose of establishing such a benchmark Beyond the SM (BSM) signal.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Can Super Resolution be used to improve Human Pose Estimation in Low Resolution Scenarios?

The results obtained from state of the art human pose estimation (HPE) models degrade rapidly when evaluating people of a low resolution, but can super resolution (SR) be used to help mitigate this effect? By using various SR approaches we enhanced two low resolution datasets and evaluated the change in performance of both an object and keypoint detector as well as end-to-end HPE results. We remark the following observations. First we find that for people who were originally depicted at a low resolution (segmentation area in pixels), their keypoint detection performance would improve once SR was applied. Second, the keypoint detection performance gained is dependent on that persons pixel count in the original image prior to any application of SR; keypoint detection performance was improved when SR was applied to people with a small initial segmentation area, but degrades as this becomes larger. To address this we introduced a novel Mask-RCNN approach, utilising a segmentation area threshold to decide when to use SR during the keypoint detection step. This approach achieved the best results on our low resolution datasets for each HPE performance metrics.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Drift Removal in Plant Electrical Signals via IIR Filtering Using Wavelet Energy

Plant electrical signals often contains low frequency drifts with or without the application of external stimuli. Quantification of the randomness in plant signals in a stimulus-specific way is hindered because the knowledge of vital frequency information in the actual biological response is not known yet. Here we design an optimum Infinite Impulse Response (IIR) filter which removes the low frequency drifts and preserves the frequency spectrum corresponding to the random component of the unstimulated plant signals by bringing the bias due to unknown artifacts and drifts to a minimum. We use energy criteria of wavelet packet transform (WPT) for optimization based tuning of the IIR filter parameters. Such an optimum filter enforces that the energy distribution of the pre-stimulus parts in different experiments are almost overlapped but under different stimuli the distributions of the energy get changed. The reported research may popularize plant signal processing, as a separate field, besides other conventional bioelectrical signal processing paradigms.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

A Low Dimensional Approximation For Competence In Bacillus Subtilis

The behaviour of a high dimensional stochastic system described by a Chemical Master Equation (CME) depends on many parameters, rendering explicit simulation an inefficient method for exploring the properties of such models. Capturing their behaviour by low-dimensional models makes analysis of system behaviour tractable. In this paper, we present low dimensional models for the noise-induced excitable dynamics in Bacillus subtilis, whereby a key protein ComK, which drives a complex chain of reactions leading to bacterial competence, gets expressed rapidly in large quantities (competent state) before subsiding to low levels of expression (vegetative state). These rapid reactions suggest the application of an adiabatic approximation of the dynamics of the regulatory model that, however, lead to competence durations that are incorrect by a factor of 2. We apply a modified version of an iterative functional procedure that faithfully approximates the time-course of the trajectories in terms of a 2-dimensional model involving proteins ComK and ComS. Furthermore, in order to describe the bimodal bivariate marginal probability distribution obtained from the Gillespie simulations of the CME, we introduce a tunable multiplicative noise term in a 2-dimensional Langevin model whose stationary state is described by the time-independent solution of the corresponding Fokker-Planck equation.

0 citations0 reviewsNo code linkedOpen access
preprint2015arXiv

Fast Approximate Bayesian Computation for Estimating Parameters in Differential Equations

Approximate Bayesian computation (ABC) using a sequential Monte Carlo method provides a comprehensive platform for parameter estimation, model selection and sensitivity analysis in differential equations. However, this method, like other Monte Carlo methods, incurs a significant computational cost as it requires explicit numerical integration of differential equations to carry out inference. In this paper we propose a novel method for circumventing the requirement of explicit integration by using derivatives of Gaussian processes to smooth the observations from which parameters are estimated. We evaluate our methods using synthetic data generated from model biological systems described by ordinary and delay differential equations. Upon comparing the performance of our method to existing ABC techniques, we demonstrate that it produces comparably reliable parameter estimates at a significantly reduced execution time.

0 citations0 reviewsNo code linkedOpen access
preprint2012arXiv

Model of haplotype and phenotype in the evolution of a duplicated autoregulatory activator

Gene duplication is believed to play a major role in the evolution of genomic complexity. The presence of a duplicate removes the constraint of natural selection upon the gene, leading to its likely loss of function or, occasionally, the gain of a novel one. Alternately, a pleiotropic gene might partition its functions among its duplicates, thus preserving both copies. Duplicate genes is not a novelty for diploid genotypes, but only for haplotypes. In this paper, we study the consequences of regulatory interactions in diploid genotypes and explore how the context of allelic interactions gives rise to dynamical phenotypes that enable duplicate genes to spread in a population. The regulatory network we study is that of a single autoregulatory activator gene, and the two copies of the gene diverge either as alleles in a diploid species or as duplicates in haploids. These differences are in their transcriptional ability -- either via alterations to its activating domain, or to its cis-regulatory binding repertoire. When cis-regulatory changes are introduced that partition multiple regulatory triggers among the duplicates, it is shown that mutually exclusive expression states of the duplicates that emerge are accompanied by a back-up facility: when a highly expressed gene is deleted, the previously unexpressed duplicate copy compensates for it. The diploid version of the regulatory network model can account for allele-specific expression variants, and a model of inheritance of the haplotype network enables us to trace the evolutionary consequence of heterozygous phenotypes. This is modelled for the variations in the activating domain of one copy, whereby stable as well as transiently bursting oscillations ensue in single cells. The evolutionary model shows that these phenotypic states accessible to a diploid, heterozygous genotype enable the spread of a duplicated haplotype.

0 citations0 reviewsNo code linkedOpen access
preprint1994arXiv

On State Counting and Characters

We outline the relationship between the thermodynamic densities and quasi-particle descriptions of spectra of RSOS models with an underlying Bethe equation. We use this to prove completeness of states in some cases and then give an algorithm for the construction of branching functions of their emergent conformal field theories. Starting from the Bethe equations of $D_n$ type, we discuss some aspects of the $Z_n$ lattice models.

0 citations0 reviewsNo code linkedOpen access