Oswaldo Ludwig

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

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

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

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

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

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.

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.

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

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

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.

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

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

seq2seq. Sequence to Sequence Learning with Keras

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

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