This is your work, valued

Ghent, Belgium.

Oswaldo Ludwig

Expert
@oswaldoludwig

I'm a principal research engineer with a PhD in electrical and computer engineering. I work with machine learning applied to generative AI, ASR, and CV.

oswaldoludwig.github.io

Seq2seq-Chatbot-for-Keras. This repository contains a new generative model of chatbot based on seq2seq modeling.

330

Human-Action-Recognition-with-Keras. Keras implementation of Human Action Recognition for the data set State Farm Distracted Driver Detection (Kaggle)

185

Adversarial-Learning-for-Generative-Conversational-Agents. This repository contains a new adversarial training method for Generative Conversational Agents

79

visually-informed-embedding-of-word-VIEW-. Visually informed embedding of word (VIEW) is a tool for transferring multimodal background knowledge to NLP algorithms.

29

Sensitivity-to-occlusion-Keras-. This script evaluates the sensitivity of VGG-16 to occlusion using Keras

12

kappaTune. A PyTorch-based optimizer wrapper for continual learning via selective fine-tuning, guided by the condition number κ (kappa) of model tensors. KappaTune identifies and updates only the least anisotropic parameters to preserve pre-trained knowledge and mitigate catastrophic forgetting.

12

Eigenvalue-Decay-Regularizer-for-Keras. Eigenvalue Decay is a new option of weight regularizer to the deep learning practitioner that aims at maximum-margin learning.

9

Parallel-Seq2Seq. A new seq2seq model for fast training.

7

CLASSP. A Biologically-Inspired Approach to Continual Learning through Adjustment Suppression and Sparsity Promotion

3

Pruning-pre-trained-models-using-evolutionary-computation. 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.

2

seq2seq_chatbot_links. [unmaintained] Links to the implementations of neural conversational models for different frameworks

1

CNN-for-Sentence-Classification-in-Keras. Convolutional Neural Networks for Sentence Classification in Keras

1

seq2seq. Sequence to Sequence Learning with Keras

1

skflow. Simplified interface for TensorFlow (mimicking Scikit Learn) for Deep Learning

1

keras. Deep Learning library for Python. Convnets, recurrent neural networks, and more. Runs on Theano and TensorFlow.

1