Vineeth S's repositories
Spoken-Keyword-Spotting
In this repository, we explore using a hybrid system consisting of a Convolutional Neural Network and a Support Vector Machine for Keyword Spotting task.
Spectrum-Sensing-for-Cognitive-Radio
In this repository, we deal with developing an energy detector and a detector based on cyclostationarity for an OFDM based cognitive radio system and implementing and evaluating the performance of these detectors.
Video-Interpolation-using-Optical-Flow
In this repository, we deal with the task of video frame interpolation with estimated optical flow. To estimate the optical flow we use Lucas-Kanade algorithm, Multiscale Lucas-Kanade algorithm (with iterative tuning), and Discrete Horn-Schunk algorithm. We explore the interpolation performance on Spheres dataset and Corridor dataset.
Compressed-Transformers
In this repository, we explore model compression for transformer architectures via quantization. We specifically explore quantization aware training of the linear layers and demonstrate the performance for 8 bits, 4 bits, 2 bits and 1 bit (binary) quantization.
Video-Frame-Prediction
In this repository, we focus on video frame prediction the task of predicting future frames given a set of past frames. We present an Adversarial Spatio-Temporal Convolutional LSTM architecture to predict the future frames of the Moving MNIST Dataset. We evaluate the model on long-term future frame prediction and its performance of the model on out-of-domain inputs by providing sequences on which the model was not trained.
TDOA-Localization
In this repository, we deal with developing different estimators to localize Transvahan - the e-vehicle on IISc Campus using measurements from receivers at four different locations in IISc and implementing and evaluating the performance of the estimators that we have derived.
Persistent-Data-Structures
In this repository, we deal with the task of implementing a small library of persistent data structures in C. A persistent data structure is a data structure that always preserves the previous version of itself when it is modified. They are effectively immutable.
Gradient-Compression
We present a set of all-reduce compatible gradient compression algorithms which significantly reduce the communication overhead while maintaining the performance of vanilla SGD. We empirically evaluate the performance of the compression methods by training deep neural networks on the CIFAR10 dataset.
Video-Interpolation-using-Deep-Optical-Flow
In this repository, we deal with the task of video frame interpolation with estimated optical flow. To estimate the optical flow we use pre-trained FlowNet2 deep learning model and experiment by fine-tuning it. We explore the interpolation performance on Spheres dataset and Corridor dataset.
Generative-Image-Compression
In this repository, we focus on the compression of images and video (sequence of image frames) using deep generative models and show that they achieve a better performance in compression ratio and perceptual quality. We explore the use of GANs for this task.
Heterogeneous-Systems
We present an algorithm to dynamically adjust the data assigned for each worker at every epoch during the training in a heterogeneous cluster. We empirically evaluate the performance of the dynamic partitioning by training deep neural networks on the CIFAR10 dataset.
Natural-Language-Inference
In this repository, we deal with the task of implementing Natural Language Inferencing (NLI) using the SNLI dataset. Different methods such as SumEmbeddings, BiLSTM, BiGRU, Transformers, and Logistic Regression are experimented.
Federated-Learning
We present UDP-based aggregation algorithms for federated learning. We also present a scalable framework for practical federated learning. We empirically evaluate the performance by training deep convolutional neural networks on the MNIST dataset and the CIFAR10 dataset.
Variational-Generative-Image-Compression
In this repository, we focus on the compression of images and video (sequence of image frames) using deep generative models and show that they achieve a better performance in compression ratio and perceptual quality. We explore the use of VAEGANs for this task.
Video-Compression-and-PCA
In this repository, we deal with the task of calculating the principal components of natural images and video frame compression bitrate analysis.
Visual-Odometry
In this repository, we deal with the task of Visual Odometry using Nister’s five point algorithm and eight point algorithm for essential matrix estimation. We develop our own implementations for these methods. We implement RANSAC along with these methods for outlier rejection.
Interpolation-of-Faulty-Sensor
In this repository, we deal with developing a Wiener (LMMSE) filter and Kalman filter for interpolation of a faulty sensor in a uniform sensor array and implementing and evaluating the performance of the estimators that we have derived.
Bayes-classifier-and-Nearest-Neighbour-classifier
In this repository, we will explore and compare different methods of classifiers such as Bayes classifier and Nearest Neighbour classifier.
Betweenness-Centrality
In this repository, we deal with the calculation of the betweenness centrality in networks represented as undirected graphs. Betweenness centrality is a measure of the importance of a particular node in a network.
datasets
🤗 Fast, efficient, open-access datasets and evaluation metrics in PyTorch, TensorFlow, NumPy and Pandas
FashionMNIST
In this repository, we deal with the FashionMNIST classification using deep multilayer perceptron (MLP) models as well as using deep convolutional neural networks (CNN) models.
Large-Unsigned-Integer-Arithmetic
In this repository, we deal with the task of arithmetic operations (addition and multiplication) on large integers represented by singly-linked lists and doubly-linked lists.
Memory-Allocators
In this repository, we deal with the implementation of the "Weighted Buddy Method for Dynamic Storage Allocation" (proposed by Shen and Peterson) and "OneBin Dynamic Storage Allocation".
Polynomial-Arithmetic
In this repository, we perform the division of polynomials represented in memory with doubly linked lists.
powersgd
Practical low-rank gradient compression for distributed optimization: https://arxiv.org/abs/1905.13727
Sparse-Matrix
In this repository, we deal with the compressed row/column (CSR/CSC) format representation of sparse matrices and its manipulation. Compressed sparse matrix formats store the sparse matrixes in a much more efficient way with reduced space requirements.
vineeths96
Profile README
visitor-badge
A badge generator service to count visitors of your markdown file.