BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260402T024533Z
LOCATION:3003\, Level 3
DTSTART;TZID=America/Los_Angeles:20250624T140000
DTEND;TZID=America/Los_Angeles:20250624T141500
UID:dac_DAC 2025_sess126_RESEARCH1716@linklings.com
SUMMARY:Computational Advantage in Hybrid Quantum Neural Networks: Myth or
  Reality?
DESCRIPTION:Muhammad Kashif, Alberto Marchisio, and Muhammad Shafique (New
  York University, Abu Dhabi)\n\nHybrid Quantum Neural Networks (HQNNs), un
 der the umbrella of Quantum Machine Learning (QML), have garnered signific
 ant attention due to their potential to enhance computational performance 
 by integrating quantum layers within traditional neural network (NN) archi
 tectures. \nDespite numerous state-of-the-art applications, a fundamental 
 question remains: Does the inclusion of quantum layers offer any computati
 onal advantage over purely classical models? If yes/no, how and why?\nIn t
 his paper, we analyze how classical and hybrid models adapt their architec
 tural complexity in response to increasing problem complexity. To this end
 , we select a multiclass classification problem and perform comprehensive 
 benchmarking of classical models for increasing problem complexity, identi
 fying those that optimize both accuracy and computational efficiency to es
 tablish a robust baseline for comparison. These baseline models are then s
 ystematically compared with HQNNs by evaluating the rate of increase in fl
 oating-point operations (FLOPs) and number of parameters, providing insigh
 ts into how architectural complexity scales with problem complexity in bot
 h classical and hybrid networks.\nWe utilize classical machines to simulat
 e the quantum layers in HQNNs, a common practice in Noisy Intermediate-Sca
 le Quantum (NISQ) era. Our analysis reveals that, as problem complexity in
 creases, the architectural complexity of HQNNs, and consequently their FLO
 Ps consumption, despite the simulation overhead associated with quantum la
 yer's simulation on classical hardware, scales more efficiently (88.5%$inc
 rease in FLOPs from 10 features (low problem complexity) to 110 features (
 high problem complexity)), compared to classical networks (53.1%). Moreove
 r, as the problem complexity increases, classical networks consistently ex
 hibit a need for a larger number of parameters to accommodate the increasi
 ng problem complexity. Additionally, the rate of increase in number of par
 ameters is also slower in HQNNs (81.4%) than classical NNs (88.5%). These 
 findings suggest that HQNNs provide a more scalable and resource-efficient
  solution, positioning them as a promising alternative for tackling comple
 x computational problems.\n\nTopics: Design\n\nTracks: DES6: Quantum Compu
 ting\n\nSession Chairs: Saurabh Kotiyal (Altera) and Sanjaya Lohani (South
 ern Methodist University)\n\n
END:VEVENT
END:VCALENDAR