Convert GPT-2 into a multimodal model using CLIP. Under 1000 lines of pure PyTorch

Turn your rough sketch into a refined image using AI

Imagined speech recognition using EEG signals. KaraOne database, FEIS database.

Testing effectiveness of EEG data augmentation with GANs for BCI classifiers.

Two Conditional GAN frameworks to perform synthetic EEG generation for dataset augmentation.

Deep Convolutional Generative Adversarial Network

Synthetic EEG data generation with GAN

Implemented CNN and RNN with PyTorch to learn and predict EEG dataset.

The project uses EEG signals from the DEAP Dataset to classify emotions into 4 classes using Ensembled 1-D CNNs, LSTMs and 2D , 3D CNNs and Cascaded CNNs with LSTMs.

Emotion recognition based on DEAP dataset using One-Dimensional CNN, dan RNN (GRU, and LSTM).

Using GAN to create synthetic and partially synthetic EEG data to augment training sets for motor imagery interaction tasks

Implementation of GAN network to generate EEG labeled data from DEAP dataset