arXiv subjects

Chandan Singh

Publications and source records attributed to Chandan Singh.

59 records · Page 4Linked to original sources

arXiv2019

Hierarchical interpretations for neural network predictions

Deep neural networks (DNNs) have achieved impressive predictive performance due to their ability to learn complex, non-linear relationships between variables. However, the inability to effectively visualize these relationships has led to DNNs being characterized as black boxes and consequently limited their applications. To ameliorate this problem, we introduce the use of hierarchical interpretations to explain DNN predictions through our proposed method, agglomerative contextual decomposition (ACD). Given a prediction from a trained DNN, ACD produces a hierarchical clustering of the input features, along with the contribution of each cluster to the final prediction. This hierarchy is optimized to identify clusters of features that the DNN learned are predictive. Using examples from Stanford Sentiment Treebank and ImageNet, we show that ACD is effective at diagnosing incorrect predictions and identifying dataset bias. Through human experiments, we demonstrate that ACD enables users both to identify the more accurate of two DNNs and to better trust a DNN's outputs. We also find that ACD's hierarchy is largely robust to adversarial perturbations, implying that it captures fundamental aspects of the input and ignores spurious noise.

cs.LG↗

arXiv2019

Interpretable machine learning: definitions, methods, and applications

Machine-learning models have demonstrated great success in learning complex patterns that enable them to make predictions about unobserved data. In addition to using models for prediction, the ability to interpret what a model has learned is receiving an increasing amount of attention. However, this increased focus has led to considerable confusion about the notion of interpretability. In particular, it is unclear how the wide array of proposed interpretation methods are related, and what common concepts can be used to evaluate them. We aim to address these concerns by defining interpretability in the context of machine learning and introducing the Predictive, Descriptive, Relevant (PDR) framework for discussing interpretations. The PDR framework provides three overarching desiderata for evaluation: predictive accuracy, descriptive accuracy and relevancy, with relevancy judged relative to a human audience. Moreover, to help manage the deluge of interpretation methods, we introduce a categorization of existing techniques into model-based and post-hoc categories, with sub-groups including sparsity, modularity and simulatability. To demonstrate how practitioners can use the PDR framework to evaluate and understand interpretations, we provide numerous real-world examples. These examples highlight the often under-appreciated role played by human audiences in discussions of interpretability. Finally, based on our framework, we discuss limitations of existing methods and directions for future work. We hope that this work will provide a common vocabulary that will make it easier for both practitioners and researchers to discuss and choose from the full range of interpretation methods.

stat.ML↗

arXiv2017

A Constrained, Weighted-L1 Minimization Approach for Joint Discovery of Heterogeneous Neural Connectivity Graphs

Determining functional brain connectivity is crucial to understanding the brain and neural differences underlying disorders such as autism. Recent studies have used Gaussian graphical models to learn brain connectivity via statistical dependencies across brain regions from neuroimaging. However, previous studies often fail to properly incorporate priors tailored to neuroscience, such as preferring shorter connections. To remedy this problem, the paper here introduces a novel, weighted-$\ell_1$, multi-task graphical model (W-SIMULE). This model elegantly incorporates a flexible prior, along with a parallelizable formulation. Additionally, W-SIMULE extends the often-used Gaussian assumption, leading to considerable performance increases. Here, applications to fMRI data show that W-SIMULE succeeds in determining functional connectivity in terms of (1) log-likelihood, (2) finding edges that differentiate groups, and (3) classifying different groups based on their connectivity, achieving 58.6\% accuracy on the ABIDE dataset. Having established W-SIMULE's effectiveness, it links four key areas to autism, all of which are consistent with the literature. Due to its elegant domain adaptivity, W-SIMULE can be readily applied to various data types to effectively estimate connectivity.

q-bio.NC↗

arXiv2016

Complexity Leads to Simplicity: A Consensus Layer V Pyramidal Neuron Can Sustain Interpulse-Interval Coding

In terms of the long-distance communication of a single neuron, interpulse intervals (IPIs) are a possible alternative to rate and binary codes. As a proxy for IPI, the time-to-spike (TTS) for a neuron can be found in the biophysical and experimental literature. Using the current, consensus layer V pyramidal neuron, the present study examines the feasibility of IPI-coding and examines the noise sources that limit the information rate of such an encoding. In descending order of noise intensity, the noise sources are (i) synaptic variability, (ii) sodium channel shot-noise, followed by (iii) thermal noise with synaptic noise much greater than the sodium channel-noise. More importantly, the biophysical model demonstrates a linear relationship between input intensity and inverse TTS. This linear observation contradicts the assumption that a neuron should be treated as a passive, electronic circuit (an RC circuit, as in the Stein model). Finally, the biophysical simulations allow the calculation of mutual information, which is about 3.0 bits/spike.

q-bio.NC↗

arXiv2010

A Fast Decision Technique for Hierarchical Hough Transform for Line Detection

Many techniques have been proposed to speedup the performance of classic Hough Transform. These techniques are primarily based on converting the voting procedure to a hierarchy based voting method. These methods use approximate decision-making process. In this paper, we propose a fast decision making process that enhances the speed and reduces the space requirements. Experimental results demonstrate that the proposed algorithm is much faster than a similar Fast Hough Transform.

cs.CV↗