31 citations · 92 across the 18 of their papers we have counts for
8 papers · 1 filter
Observations on Building RAG Systems for Technical Documents
Sumit Soman, Sujoy Roychowdhury
Retrieval augmented generation (RAG) for technical documents creates challenges as embeddings do not often capture domain information. We review prior art for important factors aff…
Complexity Controlled Generative Adversarial Networks
Himanshu Pant, Jayadeva, Sumit Soman
One of the issues faced in training Generative Adversarial Nets (GANs) and their variants is the problem of mode collapse, wherein the training stability in terms of the generative…
An Online Learning Approach for Dengue Fever Classification
Siddharth Srivastava, Sumit Soman, Astha Rai
This paper introduces a novel approach for dengue fever classification based on online learning paradigms. The proposed approach is suitable for practical implementation as it enab…
Effect of Various Regularizers on Model Complexities of Neural Networks in Presence of Input Noise
Mayank Sharma, Aayush Yadav, Sumit Soman +1
Deep neural networks are over-parameterized, which implies that the number of parameters are much larger than the number of samples used to train the network. Even in such a regime…
Radius-margin bounds for deep neural networks
Mayank Sharma, Jayadeva, Sumit Soman
Explaining the unreasonable effectiveness of deep learning has eluded researchers around the globe. Various authors have described multiple metrics to evaluate the capacity of deep…
Learning Neural Network Classifiers with Low Model Complexity
Jayadeva, Himanshu Pant, Mayank Sharma +5
Modern neural network architectures for large-scale learning tasks have substantially higher model complexities, which makes understanding, visualizing and training these architect…
Scalable Twin Neural Networks for Classification of Unbalanced Data
Jayadeva, Himanshu Pant, Sumit Soman +1
Twin Support Vector Machines (TWSVMs) have emerged an efficient alternative to Support Vector Machines (SVM) for learning from imbalanced datasets. The TWSVM learns two non-paralle…
A Neurodynamical System for finding a Minimal VC Dimension Classifier
Jayadeva, Sumit Soman, Amit Bhaya
The recently proposed Minimal Complexity Machine (MCM) finds a hyperplane classifier by minimizing an exact bound on the Vapnik-Chervonenkis (VC) dimension. The VC dimension measur…