Modelling Autobiographical Memory Loss across Life Span
Authors: Di Wang, Ah-Hwee Tan, Chunyan Miao, Ahmed A. Moustafa1368-1375
AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | For model validation, we collect a memory dataset comprising more than one thousand life events and emulate the three key memory loss processes with model parameters learnt from memory recall behavioural patterns found in human subjects of different age groups. The emulation results show high correlation with human memory recall performance across their life span, even with another population not being used for learning. |
| Researcher Affiliation | Collaboration | 1Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly 2School of Computer Science and Engineering 3Alibaba-NTU Singapore Joint Research Institute, Nanyang Technological University, Singapore 4School of Social Sciences and Psychology, Western Sydney University, Sydney, Australia 5Department of Social Sciences, College of Arts and Sciences, Qatar University, Doha, Qatar |
| Pseudocode | Yes | Algorithm 1 Event encoding and retrieval in AM-ART; Algorithm 2 Episode encoding and retrieval in AM-ART; Algorithm 3 Memory loss process during formation; Algorithm 4 Memory loss process during retrieval |
| Open Source Code | No | The paper does not provide any specific links to open-source code or state that code will be made publicly available. |
| Open Datasets | Yes | Subsequently, we perform model evaluations based on the memory recall data reported by Berntsen and Rubin (2002). Specifically, we learn the memory loss parameter values by emulating the memory recall performance of human subjects in different age groups and further use the learnt parameter values to predict the performance of human subjects in the subsequent life stage. |
| Dataset Splits | No | The paper describes a learning and prediction paradigm (learning parameters from one set of age groups to predict others, and evaluation on 'another population') but does not specify traditional dataset splits (e.g., 80/10/10 percentages or sample counts) for training, validation, and testing. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used to conduct the experiments. |
| Software Dependencies | No | The paper mentions using a 'Genetic Algorithm (GA)' and its strategies but does not specify any particular software libraries, frameworks, or their version numbers used in the implementation. |
| Experiment Setup | Yes | For each age group, the chromosome length is set to 3 (ti+1) and each gene represents one of λti, φti and µti in real number. The various GA strategies employed are tournament selection of parents (size=2 and probability=0.75), uniform crossover (rate=1), bounded mutation (to ensure all gene values are kept within [0, 1], rate=0.75), and elitism replacement (ratio=0.1). For each age group, the population size is set to 200 and GA terminates after 20 iterations. In addition, we maintain a pool of identical best-performers across GA iterations in parallel. The pool size is set to 200. |