Dooyong Koh

Dooyong Koh

Auto-generated profile, based on publicly available information

Dooyong Koh

Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge Massachusetts USA

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 February 2025 in Nano Letters
Verified
Journal Article
Closed access
DKDooyong Koh
Dooyong Koh
QWQiuyuan Wang
Qiuyuan Wang
BMBrooke C. McGoldrick
Brooke C. McGoldrick
CCChung-Tao Chou
Chung-Tao Chou
LLLuqiao Liu
Luqiao Liu
MBMarc A. Baldo
Marc A. Baldo

3 October 2025 in Physical Review Applied
Verified
Journal Article
Closed access
DKDooyong Koh
Dooyong Koh
EREthan G. Rogers
Ethan G. Rogers
KGKshemal K. Gupte
Kshemal K. Gupte
QWQiuyuan Wang
Qiuyuan Wang
BMBrooke C. McGoldrick
Brooke C. McGoldrick
LLLuqiao Liu
Luqiao Liu

30 September 2026 in Advanced Science
Verified
Journal Article
Open access
PDF file
QWQiuyuan Wang
Qiuyuan Wang
DKDooyong Koh
Dooyong Koh
BMBrooke McGoldrick
Brooke McGoldrick
TMTudor-Gabriel Mocioi
Tudor-Gabriel Mocioi
YFYabin Fan
Yabin Fan
LLLuqiao Liu
Luqiao Liu
Processing‐in‐memory architectures mitigate data shuttling bottlenecks in deterministic AI workloads, but still depend on costly external entropy sources for probabilistic models. Here, we present a magnetic‐tunnel‐junction‐based processing‐in‐memory architecture that unifies data storage and massively parallel probabilistic computation for stochastic and deterministic neural networks. By introducing bit‐paired stochastic and stable magnetic tunnel junctions, we realize a multi‐precision stochastic memory cell that transduces stored binary weights into variance‐tunable stochastic bitstreams in situ. We evaluate the architecture's versatility across three progressive regimes of stochastic neural computation. First, by using a hardware‐in‐the‐loop prototype interfacing fabricated stochastic spin‐orbit torque magnetic tunnel junctions with a field‐programmable gate array chip, we validate stochastic matrix‐vector multiplications and achieve near‐floating‐point accuracy without specialized retraining. Second, for networks with stochastic neurons, we demonstrate an Ising machine that utilizes adaptive‐precision sampling and dynamic graph routing to reduce time‐to‐solution. Third, we propose an in‐memory Bayesian computer with independent control of weight means and uncertainties, and apply it to a localization problem under unreliable inputs. By keeping intermediate signals in the stochastic domain, the architecture reduces peripheral overhead associated with random‐number generation and data conversion. This device‐circuit co‐design provides a shared hardware platform for stochastic neural inference, combinatorial optimization, and uncertainty‐aware computing.