Symbol distributions in the emergent code

For more info about our services contact : help@bestpfe.com

Table of contents

1 Introduction 
1.1 Universal language properties
1.2 Why neural networks?
1.3 Signaling Game
2 Word Length 
2.1 Anti-efficient encoding in emergent communication
2.1.1 Introduction
2.1.2 Setup
2.1.3 Experiments
2.1.4 Discussion
2.1.5 Supplementary Material
2.2 “LazImpa”: Lazy and Impatient neural agents learn to communicate efficiently
2.2.1 Introduction
2.2.2 Setup
2.2.3 Analytical method
2.2.4 Experiments
2.2.5 Discussion
2.2.6 Supplementary Material
3 Word Order 
3.1 Introduction
3.2 Related Work
3.3 Setup
3.4 Experiments
3.5 Discussion
3.6 Supplementary Material
4 Semantic Categorization – Color Naming 
4.1 Introduction
4.2 Color-naming task
4.3 Evaluating the accuracy/complexity trade-off
4.4 Experiments and Results
4.5 Discussion
4.6 Materials and Methods
4.7 Supplementary Material
5 Compositionality 
5.1 Introduction
5.2 Setup
5.3 Measurements
5.4 Generalization emerges “naturally” if the input space is large
5.5 Generalization does not require compositionality
5.6 Compositionality and ease of transmission
5.7 Discussion
5.8 Supplementary Material
6 General Discussion 
6.1 Universal language properties in emergent languages
6.2 More interpretable AI
6.3 Future directions