Name: Oswaldo Ludwig
Type: User
Company: Cerence Inc.
Bio: I'm a principal research engineer with Ph.D. degree in Electrical and Computer Engineering. My interests include Machine Learning applied to NLP, ASR and CV.
Twitter: oswaldoludwig
Location: Merelbeke, Belgium.
Blog: https://oswaldoludwig.github.io
Oswaldo Ludwig's Projects
This repository contains a new adversarial training method for Generative Conversational Agents
Caffe: a fast open framework for deep learning.
A Biologically-Inspired Approach to Continual Learning through Adjustment Suppression and Sparsity Promotion
Convolutional Neural Networks for Sentence Classification in Keras
MS COCO API - http://mscoco.org/
CTC + Tensorflow Example for ASR
Starter project for the Kaggle State Farm Distracted Driver Detection Competition
Eigenvalue Decay is a new option of weight regularizer to the deep learning practitioner that aims at maximum-margin learning.
A software package that trains an MLP by maximizing a soft approximation of the F1 squared.
t-SNE Maps of Fashion Items, Based on Fashion DNA
Library for fast text representation and classification.
Automatically exported from code.google.com/p/fully-justified-text
Keras implementation of Human Action Recognition for the data set State Farm Distracted Driver Detection (Kaggle)
Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano and TensorFlow.
Ludwig is a toolbox built on top of TensorFlow that allows to train and test deep learning models without the need to write code.
A new seq2seq model for fast training.
This repository contains scripts to prune Wav2vec2 using a neuroevolution-based method. More details about this method can be found in the paper Compressing Wav2vec2 for Embedded Applications.
This script evaluates the sensitivity of VGG-16 to occlusion using Keras
Sequence to Sequence Learning with Keras
This repository contains a new generative model of chatbot based on seq2seq modeling.
[unmaintained] Links to the implementations of neural conversational models for different frameworks
Simplified interface for TensorFlow (mimicking Scikit Learn) for Deep Learning
Spearmint Bayesian optimization codebase
A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
Implementation of a seq2seq model for Speech Recognition using the latest version of TensorFlow. Architecture similar to Listen, Attend and Spell.
Visually informed embedding of word (VIEW) is a tool for transferring multimodal background knowledge to NLP algorithms.