Volterra Neural Networks (VNNs)
The importance of inference in Machine Learning (ML) has led to an explosive number of different proposals in ML, and particularly in Deep Learning. In an attempt to reduce the complexity of Convolutional Neural Networks, we propose a Volterra filter-inspired Network architecture. This architecture introduces controlled non-linearities in the form of interactions between the delayed input samples of data. We propose a cascaded implementation of Volterra Filtering so as to significantly reduce the number of parameters required to carry out the same classification task as that of a conventional Neural Network. We demonstrate an efficient parallel implementation of this Volterra Neural Network (VNN), along with its remarkable performance while retaining a relatively simpler and potentially more tractable structure. Furthermore, we show a rather sophisticated adaptation of this network to nonlinearly fuse the RGB (spatial) information and the Optical Flow (temporal) information of a video sequence for action recognition. The proposed approach is evaluated on UCF-101 and HMDB-51 datasets for action recognition, and is shown to outperform state of the art CNN approaches.
Code (1)
Tasks
Action RecognitionOptical Flow EstimationSimilar Papers 제목 키워드 기반
Latent Code-Based Fusion: A Volterra Neural Network Approach
We propose a deep structure encoder using the recently introduced Volterra Neural Networks (VNNs) to seek a latent representation of multi-modal data whose features are jointly captured by a union of subspaces. The so-ca…
ClusteringRobust classificationWaveNet-Volterra Neural Networks for Active Noise Control: A Fully Causal Approach
Active Noise Control (ANC) systems are challenged by nonlinear distortions, which degrade the performance of traditional adaptive filters. While deep learning-based ANC algorithms have emerged to address nonlinearity, ex…
Sparse Covariance Neural Networks
Covariance Neural Networks (VNNs) perform graph convolutions on the covariance matrix of tabular data and achieve success in a variety of applications. However, the empirical covariance matrix on which the VNNs operate m…
Action RecognitionComputational EfficiencyTemporal Action LocalizationTransferability of coVariance Neural Networks and Application to Interpretable Brain Age Prediction using Anatomical Features
Graph convolutional networks (GCN) leverage topology-driven graph convolutional operations to combine information across the graph for inference tasks. In our recent work, we have studied GCNs with covariance matrices as…
Predicting Brain Age using Transferable coVariance Neural Networks
The deviation between chronological age and biological age is a well-recognized biomarker associated with cognitive decline and neurodegeneration. Age-related and pathology-driven changes to brain structure are captured …