基本信息
浏览量:88
职业迁徙
个人简介
My research seeks to analyze the algorithmic components used in biological neural networks, in
order to port them to the machine learning context. I built a computational model of the Moth
Olfactory Network, with structure and behavior closely matched to known biophysics and in
vivo neural data.
Assigned the task of classifying the MNIST digits, this moth brain model learns to read given
only 1 to 10 training samples per class, outperforming standard machine learning (ML) methods
in this few-samples regime.
The experiments elucidate biological mechanisms for fast learning that rely on cascaded
networks, competitive inhibition, sparsity, and Hebbian plasticity.
I hope to examine other neural mechanisms and structures (e.g. in mammals) that can be
usefully characterized and ported to the ML context.
order to port them to the machine learning context. I built a computational model of the Moth
Olfactory Network, with structure and behavior closely matched to known biophysics and in
vivo neural data.
Assigned the task of classifying the MNIST digits, this moth brain model learns to read given
only 1 to 10 training samples per class, outperforming standard machine learning (ML) methods
in this few-samples regime.
The experiments elucidate biological mechanisms for fast learning that rely on cascaded
networks, competitive inhibition, sparsity, and Hebbian plasticity.
I hope to examine other neural mechanisms and structures (e.g. in mammals) that can be
usefully characterized and ported to the ML context.
研究兴趣
论文共 31 篇作者统计合作学者相似作者
按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选
时间
引用量
主题
期刊级别
合作者
合作机构
Frontiers in Malaria (2024)
Daniel E. Shea,Sourabh Kulhare,Rachel Millin,Zohreh Laverriere,Courosh Mehanian,Charles B. Delahunt,Dipayan Banik,Xinliang Zheng,Meihua Zhu, Ye Ji,Travis Ostbye, Martha-Marie S. Mehanian,
CVPR Workshopspp.3103-3112, (2023)
引用5浏览0EIWOS引用
5
0
Frontiers in Malaria (2023)
引用0浏览0引用
0
0
SIMULATION AND SYNTHESIS IN MEDICAL IMAGING, SASHIMI 2023 (2023): 75-85
arxiv(2022)
引用0浏览0EI引用
0
0
arxiv(2022)
引用0浏览0EI引用
0
0
Research Square (Research Square) (2022)
arXiv (Cornell University) (2022)
引用0浏览0引用
0
0
加载更多
作者统计
合作学者
合作机构
D-Core
- 合作者
- 学生
- 导师
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn