A comprehensive collection of implementations for Deep Neural Networks, including Autoencoders, MLPs, CNNs, RNNs (LSTM/GRU), Sparse R-CNN, and Transformers. Features applications in dimensionality reduction, face recognition with Angular Margin Loss, sentiment analysis, object detection, and NLP classification
nlp deep-learning sentiment-analysis transformers cnn pytorch lstm gru neural-networks rnn face-recognition object-detection mlp autoencoders bert self-attention angular-margin-loss sparse-rcnn
-
Updated
Jun 28, 2026 - Jupyter Notebook