Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/gaizkiaadeline/text-classification-model-using-lstm-and-word2vec-vectorization
This repository contains a text classification model using LSTM, Word2Vec embeddings, and the Adam optimizer for efficient training and classification of textual data. The model classifies textual data based on pre-trained word vectors and is built with TensorFlow and Keras.
https://github.com/gaizkiaadeline/text-classification-model-using-lstm-and-word2vec-vectorization
adam-optimizer keras lstm tensorflow word2vec
Last synced: 14 days ago
JSON representation
This repository contains a text classification model using LSTM, Word2Vec embeddings, and the Adam optimizer for efficient training and classification of textual data. The model classifies textual data based on pre-trained word vectors and is built with TensorFlow and Keras.
- Host: GitHub
- URL: https://github.com/gaizkiaadeline/text-classification-model-using-lstm-and-word2vec-vectorization
- Owner: gaizkiaadeline
- Created: 2024-10-22T04:28:28.000Z (17 days ago)
- Default Branch: main
- Last Pushed: 2024-10-22T05:58:04.000Z (17 days ago)
- Last Synced: 2024-10-23T08:14:14.238Z (16 days ago)
- Topics: adam-optimizer, keras, lstm, tensorflow, word2vec
- Language: Jupyter Notebook
- Homepage:
- Size: 4.67 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Text Classification using LSTM, Word2Vec, and Adam Optimizer
This project presents a text classification model built with Long Short-Term Memory (LSTM) networks and Word2Vec embeddings, optimized using the Adam optimizer. The dataset includes textual data labeled into various categories. By employing pre-trained Word2Vec embeddings, the textual data is converted into vectorized representations. These vectors are passed through an LSTM architecture, known for capturing sequential patterns in text. The Adam optimizer ensures efficient and adaptive training of the model, enabling faster convergence.
**Key Features:**
- Data Preprocessing: Text cleaning, tokenization, and vectorization using Word2Vec.
- LSTM Model: Sequential LSTM layers for effective sequence learning and text classification.
- Word2Vec Embeddings: Pre-trained word vectors for meaningful text representation.
- Adam Optimizer: Adaptive optimization technique to enhance model performance.
- Performance Evaluation: Accuracy and loss metrics are used to evaluate the model's performance.
