Advanced search
Found 2 essays matching the above criteria.
-
1. Emotion Classification with Natural Language Processing (Comparing BERT and Bi-Directional LSTM models for use with Twitter conversations)
University essay from Lunds universitet/Matematisk statistikAbstract : We have constructed a novel neural network architecture called CWE-LSTM (concatenated word-emoji bidirectional long short-term memory) for classify- ing emotions in Twitter conversations. The architecture is based on a combina- tion of word and emoji embeddings with domain specificity in Twitter data. READ MORE
-
2. A Study of Gradient-Based Algorithms
University essay from Lunds universitet/Matematisk statistikAbstract : Gradient-based algorithms are popular when solving unconstrained optimization problems. By exploiting knowledge of the gradient of the objective function to optimize, each iteration of a gradient-based algorithm aims at approaching the minimizer of said function. READ MORE