#deep learning

2022-02-22

#Voice AI #Speech Representation #Deep Learning

How deep learning models can isolate independent factors of variation in data through VAEs and Beta-TCVAE, enabling controlled synthesis and better downstream representations.

View

Code Mixing in NLP and Speech

2021-08-24

#Speech #NLP #Deep Learning

Notes from a seminar covering six papers on code-mixing across NLP, speech synthesis, and speech recognition — including multilingual synthesis and code-mixed ASR.

View

Towards Automated Deep Learning: Analysis of the AutoDL Challenge Series 2019

2020-06-01 Zhengying Liu, Zhen Xu, Shangeth Rajaa, Meysam Madadi, Julio C. S. Jacques Junior, Sergio Escalera, Adrien Pavao, Sebastien Treguer, Wei-Wei Tu, Isabelle Guyon Proceedings of Machine Learning Research (PMLR), NeurIPS 2019 Competition Track, Vol. 123, pp. 242–252

#AutoML #Deep Learning #NeurIPS

Design and results of the AutoDL challenge series 2019 (AutoCV, AutoCV2, AutoNLP, AutoSpeech, AutoDL), showing winning solutions generalize to unseen datasets.

View

GAN 5: Conditional GAN and Pix2Pix

2019-05-25

#Deep Learning #GAN #PyTorch #Python

How Conditional GANs extend vanilla GANs to generate class-specific samples, and how Pix2Pix does image-to-image translation.

GAN 4: Deep Convolutional GAN (DCGAN) on SVHN

2019-05-24

#Deep Learning #GAN #PyTorch #Python

Implementing DCGAN with CNNs, batch normalization, and transposed convolutions to generate Street View House Numbers.

GAN 2: The Game Theory Behind Generator and Discriminator

2019-05-21

#Deep Learning #GAN #PyTorch

How the adversarial game between Generator and Discriminator works, and why equilibrium matters.

GAN 3: Implementing a Linear GAN on MNIST in PyTorch

2019-05-21

#Deep Learning #GAN #PyTorch #Python

Step-by-step PyTorch implementation of a vanilla GAN trained on MNIST — data loading, Discriminator, Generator, training loop.

GAN 1: Introduction to Generative Adversarial Networks

2019-05-20

#Deep Learning #GAN

What GANs are, how they work, and some remarkable recent research — StackGAN, iGAN, Pix2Pix.

Unsupervised Learning 101

2019-05-20

#Deep Learning #Machine Learning

An intro to unsupervised learning — clustering, feature learning, and dimensionality reduction, and why it matters.

Convolutional Feature Extraction and Neural Arithmetic Logic Units for Stock Prediction

2019-04-12 Shangeth Rajaa, Jajati Keshari Sahoo International Conference on Advances in Computing and Data Sciences (ICACDS 2019), Springer, pp. 349–359

#Deep Learning #Finance #CNN

A data-driven deep learning approach combining CNN feature extraction with Neural Arithmetic Logic Units (NALU) for stock price prediction using historical price data.

View