Embed an App
Or write your own HTML code! (HTML is Pro only)
Skip to content
Independent consulting & contract R&D
From neural principles
to deployable AI.I help teams build efficient AI for signals, sensors and autonomous systems, connecting mathematical ideas with working algorithms and real hardware constraints.
Spatiotemporal AI / Event-based vision / Neuromorphic computing
Neural signaling · conceptual illustration
Research & engineering experience
BrainChipKelzalBrain Corp / QualcommSony CSLSalk Institute01 / Capabilities
Deep research.
Practical engineering.I work across theory, implementation and technical direction. An engagement can start with a specific bottleneck, a new architecture, or a research question that needs a working prototype.
01 Design the right
neural architectureSpatiotemporal networks, neural state-space models, spiking networks and learning rules for streaming data.
Architecture design · mathematical modeling · research prototypes
02 Make perception
work at the edgeEvent-based vision, RF/radar processing, sensor fusion and adaptive control under memory, latency and power constraints.
Algorithm development · benchmarking · hardware-aware optimization
03 Set a clear
R&D directionEvaluate competing approaches, define a roadmap, and connect research, engineering and product teams.
Technical assessment · proposal development · scientific leadership
02 / Selected work
Ideas made concrete.
A selection of architectures, perception systems and collaborative research programs. Each connects a scientific question to an engineering problem.
Neural architectures / BrainChip
PLEIADES & TENNs
Structured temporal memory for efficient streaming intelligence.
I invented PLEIADES and co-invented Temporal Event-based Neural Networks (TENNs), connecting temporal convolution with efficient neural processing. PLEIADES builds temporal kernels from orthogonal polynomials for event-based classification and detection.
The TENN architecture work combined parallel training with low-memory recurrent inference and informed BrainChip’s Akida platform direction.
Read the PLEIADES paperTemporal structure → useful memorySignal / eventsTemporal kernelsPrediction99.59%DVS128 gesture recognition accuracy
192K parametersReported benchmark result from the linked paper.
Kernel graphic is illustrative.
Event-based perception · conceptual illustration, not sensor data Perception systems / Kelzal (Qelzal)
Seeing through change.
Low-latency perception from asynchronous vision sensors.
I founded and led Kelzal, developing event-based processing for drones, vehicles, retail and security applications. The work covered tracking, stereo depth, optic flow, IMU stabilization, frequency estimation, denoising and image reconstruction.
NSF and DARPA projects explored sense-and-avoid systems and optical guidance for small unmanned aircraft, bringing sensors and algorithms into embedded prototypes.
RF & radar / BrainChip
Neuromorphic signal intelligence
Invented SCORPIUS for RF and radar signal modeling and automatic modulation classification. Co-authored the technical proposal and served as a principal investigator on a $1.8M Air Force program for low-power neuromorphic radar classification.
RF/radar processing · temporal models · research leadership
Robotics / Brain Corp & Qualcomm
Spiking networks for adaptive control
Developed spiking models of motor control, reinforcement learning and predictive control. Contributed to DARPA research on visually guided flight and hover control for autonomous helicopter drones.
Spiking neural networks · learning rules · autonomous systems
Collaborative research / Sony CSL
SENSOPAC & SPIKEFORCE
Created and coordinated two European research consortia totaling €8.9M. The programs brought neuroscience, machine learning, tactile sensing and real-time spiking networks together to study perception, manipulation and robot control.
Human–machine interaction / Intentiva
Gesture-based interaction
Co-founded and led Intentiva, developing visual hand-gesture recognition to control televisions and other devices from a distance, combining brain-inspired computing and machine learning.
Computer vision · interaction · startup development
Current focus
Intelligence closer
to the sensor.Governed execution layer & stable API
A stable API above model formats and vendor runtimes, with reproducible build records, verified artifacts and qualification evidence.
Alongside ongoing research in efficient spatiotemporal and neuromorphic systems.
03 / Research interests
Questions that
shape the work.My interests sit where neuroscience, mathematical physics and machine intelligence meet.
Time, memory & causality
Neural dynamics, state-space models and representations that preserve the timing of events.
Learning from the brain
Neural coding, synaptic plasticity, independent representations and spiking computation.
Embodied intelligence
Active perception, sensorimotor learning and adaptive control for robots and autonomous systems.
Efficient intelligence
Sparse and event-driven processing, cognitive RF and AI that works within device constraints.
04 / Background & toolkit
Physics, neuroscience
& AI engineering.I’m Olivier Coenen, an AI scientist and research leader working from mathematical foundations through algorithms to embedded systems.
My background combines a PhD in Physics (Biophysics) at UC San Diego, research with Terrence J. Sejnowski at the Salk Institute, founding Sony CSL Paris’s Neuroscience Group, and scientific and entrepreneurial roles across AI and robotics.
I’ve led research teams, funded R&D programs and startups, with work spanning publications, patents, prototypes and product-facing systems.
Professional profile on LinkedInPhDPhysics / Biophysics
UC San DiegoBScHonours Physics
McGill UniversitySkills across the full R&D cycle
Modeling & learning
Mathematical physics; dynamical systems; optimal control; information theory; sparsity; independent coding; computational neuroscience; deep learning; reinforcement learning; neural state-space models; spiking networks.
Software & implementation
Python, PyTorch, TensorFlow, NumPy/SciPy, C/C++, CUDA/TensorRT, XLA/AMP, ROS and Linux. Reproducible training, benchmarking, ablations and model optimization.
Signals, sensors & control
Event-based processing, computer vision, image and signal processing, RF/radar, tracking, stereo/depth, optic flow, Kalman filtering, sensor fusion, IMU stabilization and adaptive robotics.
Scientific & business leadership
Research direction, technical strategy, competitive analysis, consortium coordination, proposals and grants, project and budget management, hiring, mentoring, entrepreneurship, fundraising, partnerships, product strategy and intellectual property.
Let’s work together
What are you
trying to build?Tell me about the problem, your target platform and the constraints that matter. We can explore a focused consulting engagement or hands-on contract R&D.