學(xué)術(shù)報(bào)告
Neural network aided approximation and parameter inference of non-Markovian models
報(bào)告題目：Neural network aided approximation and parameter inference of non-Markovian models
時(shí)間：2024年11月2日 9:30-11:00
地點(diǎn)：主樓B座1421
邀請(qǐng)人：何仁初 教授
報(bào)告人簡(jiǎn)介：曹志興，華東理工大學(xué)教授、博士生導(dǎo)師，中組部青年千人計(jì)劃入選者。2012年本科畢業(yè)于浙江大學(xué)控制科學(xué)與工程學(xué)系，2016年博士畢業(yè)于香港科技大學(xué)化學(xué)與生物分子工程學(xué)系，其先后于美國哈佛大學(xué)、英國愛丁堡大學(xué)擔(dān)任博士后。研究領(lǐng)域包括機(jī)器學(xué)習(xí)、系統(tǒng)生物學(xué)的交叉研究，多次以一作和通訊作者身份在Nature Communications、美國科學(xué)院院刊PNAS、Current Opinion in Biotechnology等著名期刊發(fā)表研究結(jié)果，成果入選《國家自然科學(xué)基金委員會(huì)2021年度報(bào)告》資助成果巡禮，獲得2021麻省理工科技評(píng)論亞太區(qū)35歲以下科技創(chuàng)新35人、2023阿里巴巴達(dá)摩院青橙獎(jiǎng)最具潛力獎(jiǎng)等榮譽(yù)。
報(bào)告摘要：Non-Markovian models of stochastic biochemical kinetics often incorporate explicit time delays to effectively model large numbers of intermediate biochemical processes. Analysis and simulation of these models, as well as the inference of their parameters from data, are fraught with difficulties because the dynamics depends on the system’s history. Here we use an artificial neural network to approximate the time-dependent distributions of non- Markovian models by the solutions of much simpler time-inhomogeneous Markovian models; the approximation does not increase the dimensionality of the model and simultaneously leads to inference of the kinetic parameters. The training of the neural network uses a relatively small set of noisy measurements generated by experimental data or stochastic simulations of the non-Markovian model. We show using a variety of models, where the delays stem from transcriptional processes and feedback control, that the Markovian models learnt by the neural network accurately reflect the stochastic dynamics across parameter space. Finally, I will talk about how to publish a high-profile paper given the example presented above.