Pinned Repositories
Audio-Classification-Using-Wavelet-Transform
Classifying audio using Wavelet transform and deep learning
Bird-Song-Classification
Classify bird species based on their songs using SIamese Networks and 1D dilated convolutions.
Bird-sound-classification
Classify bird's sound using siamese networks and few-shot learning.
Gossip-Simulator
Implementation of gossip protocols for information dissemination in a network with different kinds of topologies.
Image-segmentation-overview
Demonstration of a few useful segmentation algorithms.
MultiColor-Shapes-Database
A small database to test different machine learning tasks. It contains simple shapes of different colors.
Music-Genre-Classification
Classify music in two categories progressive rock and non-progressive rock using mfcc features, MLP, and CNN.
PCATutorial
A Step-by-step tutorial to implement PCA.
Siamese-Networks-Tutorial
SIFT-Algorithm
Demonstration of sift algorithm to track objects and observing the effect of each parameter on performance.
AdityaDutt's Repositories
AdityaDutt/Audio-Classification-Using-Wavelet-Transform
Classifying audio using Wavelet transform and deep learning
AdityaDutt/Bird-Song-Classification
Classify bird species based on their songs using SIamese Networks and 1D dilated convolutions.
AdityaDutt/Siamese-Networks-Tutorial
AdityaDutt/MultiColor-Shapes-Database
A small database to test different machine learning tasks. It contains simple shapes of different colors.
AdityaDutt/SIFT-Algorithm
Demonstration of sift algorithm to track objects and observing the effect of each parameter on performance.
AdityaDutt/Bird-sound-classification
Classify bird's sound using siamese networks and few-shot learning.
AdityaDutt/Image-segmentation-overview
Demonstration of a few useful segmentation algorithms.
AdityaDutt/Music-Genre-Classification
Classify music in two categories progressive rock and non-progressive rock using mfcc features, MLP, and CNN.
AdityaDutt/Gossip-Simulator
Implementation of gossip protocols for information dissemination in a network with different kinds of topologies.
AdityaDutt/PCATutorial
A Step-by-step tutorial to implement PCA.
AdityaDutt/SpeechEmotionRecognitionPapers
A curated list on the literature of emotion recognition using deep learning.
AdityaDutt/Bitcoin-Simulator
Implementation of Bitcoin protocol to simulate bitcoin mining, wallet, and transactions.
AdityaDutt/PCALinearityCheck
A demonstration of how to use PCA to see if data is linear or not
AdityaDutt/Tensorboard_visualize
Visualize data on TensorBoard.
AdityaDutt/Emotion-Recognition-Papers
A list of papers for emotion recognition using machine learning/deep learning.
AdityaDutt/Jobscheduler-using-RB-Tree-and-min-heap
Task scheduler using RB tree and min heap.
AdityaDutt/Linear-and-Circular-Convolution-using-FFT
This program demonstrates (i) the speedup obtained by using FFTs in numerical convolution. The two sequences x and y must contain at least 1000 elements each. The convolution code is written on own and libraries are used for the FFT computation. The speedup is documented using TIC TOC. (ii) The errors between circular convolution using FFTs and linear convolution (direct computation) is documented. In both (i) and (ii), 5 sets of random x and y sequences are used.
AdityaDutt/SVD-based-image-reconstruction
Load the hendrix_final.png image and extract the R, G and B channels. Convert each channel image to double precision. Then execute the SVD separately on the R, G and B channels of the image. Plot (using a log-log plot) the non-zero singular values for the R channel. Comment on the nature of the plot. Plot the Frobenius norm of the reconstruction error matrix for each channel w.r.t. the dimension (increasing from 1 to the rank) and display the original and final reconstructed images (combined from R, G and B reconstructions)
AdityaDutt/BirdSoundClassification
AdityaDutt/Principal-Component-Analysis
An octave script to generate the principal components of the clockwork-angels. This is run for different choices of input parameters. The relevant ones are: (i) Number of patches (number_patches) chosen to be somewhat greater than 1000. The code checks for this and discards duplicates. We also present a result for 20000 patches; (ii) Patch size (patch) usually chosen to be 16 × 16 but can be increased (and we present a result for 24 × 24); (iii) The number of eigenvectors (number_eig) chosen for the final display. This is usually 64 but we present a result with 256 eigenvectors; (iv) The gap between the eigenvector images (scratch) for the final display usually set to 4. There are many possible criteria for deciding how much information is preserved. One of the best is the sum of the Frobenius norm errors of all reconstructed patches divided by the Frobenius norm of the patch. But, the ratio of the sum of chosen eigenvalues divided by the total sum of all eigenvalues is also reasonable, etc
AdityaDutt/aditya-portfolio-revamp
AdityaDutt/AdityaDutt
AdityaDutt/adityadutt.github.io
AdityaDutt/Awesome-Knowledge-Distillation
Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。
AdityaDutt/AWESOME-MER
🔆 📝 A reading list focused on Multimodal Emotion Recognition (MER) 👂👄 👀 💬
AdityaDutt/Awesome-VAEs
A curated list of awesome work on VAEs, disentanglement, representation learning, and generative models.
AdityaDutt/cancer-images
AdityaDutt/Folder-Structure-Conventions
Folder / directory structure options and naming conventions for software projects
AdityaDutt/Handwriting-loops-and-boundary-detection
A fast python library to detect loops, outer boundary and edges in binary images.
AdityaDutt/SER-datasets
A collection of datasets for the purpose of emotion recognition/detection in speech.