Search Results for author:
Found 21 papers, 3 papers with code
Transformer based Multitask Learning for Image Captioning and Object Detection
We propose TICOD, Transformer-based Image Captioning and Object detection model for jointly training both tasks by combining the losses obtained from image captioning and object detection networks.
Continuous Depth Recurrent Neural Differential Equations
Specifically, we propose continuous depth recurrent neural differential equations (CDR-NDE) which generalizes RNN models by continuously evolving the hidden states in both the temporal and depth dimensions.
DialoGen: Generalized Long-Range Context Representation for Dialogue Systems
In this work, we propose DialoGen, a novel encoder-decoder based framework for dialogue generation with a generalized context representation that can look beyond the last-$k$ utterances.
HyperHawkes: Hypernetwork based Neural Temporal Point Process
We also develop a hypernetwork based continually learning temporal point process for continuous modeling of time-to-event sequences with minimal forgetting.
Continual Learning with Dependency Preserving Hypernetworks
However, the continual learning performance of existing hypernetwork based approaches are affected by the assumption of independence of the weights across the layers in order to maintain parameter efficiency.
Bayesian Neural Hawkes Process for Event Uncertainty Prediction
Therefore, we propose a novel point process model, Bayesian Neural Hawkes process (BNHP) which leverages uncertainty modelling capability of Bayesian models and generalization capability of the neural networks to model event occurrence times.
Improving Robustness and Uncertainty Modelling in Neural Ordinary Differential Equations
As $T$ implicitly defines the depth of a NODE, posterior distribution over $T$ would also help in model selection in NODE.
Latent Time Neural Ordinary Differential Equations
As $T$ implicitly defines the depth of a NODE, posterior distribution over $T$ would also help in model selection in NODE.
Bi-Directional Recurrent Neural Ordinary Differential Equations for Social Media Text Classification
In this work, we propose to use recurrent neural ordinary differential equations (RNODE) for social media post classification which consider the time of posting and allow the computation of hidden representation to evolve in a time-sensitive continuous manner.
Monte Carlo DropBlock for Modelling Uncertainty in Object Detection
We demonstrate the effectiveness of the proposed approach on modeling uncertainty in object detection and segmentation tasks using out-of-distribution experiments.
Subset-of-Data Variational Inference for Deep Gaussian-Processes Regression
Deep Gaussian Processes (DGPs) are multi-layer, flexible extensions of Gaussian processes but their training remains challenging.
Adiabatic Quantum Feature Selection for Sparse Linear Regression
This paper aims to address the intractability of sparse linear regression with $\ell_0$ norm using adiabatic quantum computing, a quantum computing paradigm that is particularly useful for solving optimization problems faster.
Galaxy Morphology Classification using Neural Ordinary Differential Equations
We introduce a continuous depth version of the Residual Network (ResNet) called Neural ordinary differential equations (NODE) for the purpose of galaxy morphology classification.
Instrumentation and Methods for Astrophysics Astrophysics of Galaxies
Delay Differential Neural Networks
Neural ordinary differential equations (NODEs) treat computation of intermediate feature vectors as trajectories of ordinary differential equation parameterized by a neural network.
Evaluation of Deep Gaussian Processes for Text Classification
With the tremendous success of deep learning models on computer vision tasks, there are various emerging works on the Natural Language Processing (NLP) task of Text Classification using parametric models.
Learning Multi-Sense Word Distributions using Approximate Kullback-Leibler Divergence
We propose to learn the Gaussian mixture representation of words using a Kullback-Leibler (KL) divergence based objective function.
Deep Gaussian Processes with Convolutional Kernels
This has hindered the application of DGPs in computer vision tasks, an area where deep parametric models (i. e. CNNs) have made breakthroughs.
Studying the Temporal Dynamics of Word Co-occurrences: An Application to Event Detection
Streaming media provides a number of unique challenges for computational linguistics.
Gaussian Process Pseudo-Likelihood Models for Sequence Labeling
We provide Gaussian process models based on pseudo-likelihood approximation to perform sequence labeling.
