amit-raj-repo / DL-NLP-Siamese-Network

The Facenet paper of 2015 proposed an interesting solution for huge multiclass problems. Instead of the traditional approach, we try to learn a similarity function i.e. degree of difference between 2 inputs. If the degree of difference between the inputs is less than a threshold then the inputs are classified as similar else different.

deep-neural-networks deep-learning deeplearning nlp siamese-network siamese-neural-network siamese-lstm siamese-recurrent-architectures siamese siamese-networks

Siamese-Network

About

The Facenet paper of 2015 proposed an interesting solution for huge multiclass problems. Instead of the traditional approach, we try to learn a similarity function i.e. degree of difference between 2 inputs. If the degree of difference between the inputs is less than a threshold then the inputs are classified as similar else different.

deep-neural-networks deep-learning deeplearning nlp siamese-network siamese-neural-network siamese-lstm siamese-recurrent-architectures siamese siamese-networks

Languages

Language:Jupyter Notebook 100.0%