Summary of Towards Neural Network Based Cognitive Models Of Dynamic Decision-making by Humans, By Changyu Chen et al.
Towards Neural Network based Cognitive Models of Dynamic Decision-Making by Humans
by Changyu Chen, Shashank Reddy Chirra, Maria José Ferreira, Cleotilde Gonzalez, Arunesh Sinha, Pradeep Varakantham
First submitted to arxiv on: 24 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computers and Society (cs.CY)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper proposes two attention-based neural network models to model distinct and heterogeneous human decision-making in dynamic settings, departing from previous approaches that assume a common model for all humans. By leveraging Instance-Based Learning (IBL), which posits that human decisions are based on similar situations encountered in the past, these models incorporate open form non-linear functions to capture the mapping from past situations to current decisions. The proposed models are evaluated using two distinct datasets: one focusing on phishing email detection and another on cybersecurity settings where humans act as attackers deciding on attack options. Compared to IBL and GPT3.5, the neural network models outperform IBL significantly in representing human decision-making while providing similar interpretability of human decisions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making artificial intelligence (AI) systems more like humans when they make decisions. Right now, AI systems are good at following rules but not as good at making decisions that are specific to each person. Humans have different experiences and biases that affect their decisions, so we need a way to model these differences in AI systems. The researchers propose two new neural network models that can capture these individual differences and make better decisions in dynamic situations. They test these models using data from human experiments on detecting phishing emails and making cybersecurity decisions. The results show that the neural network models are more accurate than previous approaches and provide a better understanding of how humans make decisions. |
Keywords
» Artificial intelligence » Attention » Neural network
