conv1d

Basic Gesture Recognition Using mmWave Sensor - TI AWR1642

Intrusion Detection System - IDS example using Dense, Conv1d and Lstm layers in Keras / TensorFlow

MPS like shaders for audio processing. Conv1d, Spectrogram.

Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models

cross-platform modular neural network inference library, small and efficient

Augmenting character level Transformers with Causal Dilated Conv1D layers

Cross-platform mobile Neural network C library for training and inference on the device. CPU only. It fits for time-series data.

VAITP - Vulnerability Attack and Injection Tool for Python

Implemented a Research paper "PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts. Use Hybrid Embedding (char + token + positional).

GAN for Spectral Data Augmentation

Goal is to detect peak in given signal(s) in directory \dataset with computation intelligence and not just signal processing. Here, we have used 1D CNN from Keras to achieve it.

Benchmark NLP models on Kaggle “Disaster Tweets”: TF-IDF + Naive Bayes baseline, Keras deep nets (Dense/LSTM/GRU/BiRNN/Conv1D), and TensorFlow Hub Universal Sentence Encoder transfer learning—compared using accuracy, precision, recall, and F1.

Donors Choose

This project predicts sunspot activity using an LSTM model for time series data. Built with TensorFlow and Keras, it uses Huber loss for outlier handling and MAE for performance evaluation. The dataset, sourced from Kaggle or SIDC, spans over 270 years of monthly sunspot data.

This model converts Facial expression to basic messages for motor impaired patients with own dataset

Starter repository for the Manning liveProject: What's the news: Summarize news articles with NLP, Deep Learning, and Python.

predict price of bitcoin using time series

A project on Topic Modelling and Text Summarization of NIPS research papers

A Comprehensive Analysis Framework for Material Thickness Estimation Using TOF Data

Real-time LIBRAS manual alphabet recognition from hand landmarks (MediaPipe), using a hybrid pipeline: a static MLP for fixed poses and a dynamic Conv1D for motion letters.