My PhD

In three minutes

PhD thesis promo recorded on the regional final of "Ma thèse en 180" contest (in French).

Home Lab

Brain hacking and other projects

More Posts

Recently NASA has made the first powered flight on Mars. They have deployed a drone called Ingenuity costing about $85 million. The helicopter was able to fly on about ten meters altitude (as of May, 7) over the surface of the Red Planet. Coincidently, I have also built a flying drone. This looked like a good challenge and an opportunity to learn about unmanned aerial vehicles (UAVs). Here is what I learned.


Here is a step by step tutorial on how to design objects for 3D printing using OpenSCAD. We illustrate the design process by creating a micro quadcopter frame. This small drone bears the code name of Beatle-1. After following the tutorial you will be able to conceive your own designs for 3D printing.


We will build an autonomous robot. Captured by robot's camera, video stream will be analyzed by a neural network. The network will be running on the onboard Raspberry Pi that will steer the robot. Before you start with the project, I want you to answer two questions. First, how everything will be attached mechanically? Second, what will be the energy source? While your autonomous robot can work from a cardboard box, having a mechanically sound chassis will greatly improve the result on the AI training stage.


10 Days Of Grad

Haskell Deep Learning Blog

More Posts

Last week Apple has acquired startup for amazing $200 million. The startup is known for promoting binarized neural network algorithms to save the energy and computational resources. That is definitely a way to go for mobile devices, and Apple just acknowledged that it is a great deal for them too. I feel now is a good time to explain what binarized neural networks are so that you can better appreciate their value for the industry.


Today we will talk about one of the most important deep learning architectures, the "master algorithm" in computer vision. That is how François Chollet, author of Keras, calls convolutional neural networks (CNNs). Convolutional network is an architecture that, like other artificial neural networks, has a neuron as its core building block. It is also differentiable, so the network is conveniently trained via backpropagation. The distinctive feature of CNNs, however, is the connection topology, resulting in sparsely connected convolutional layers with neurons sharing their weights.


Which purpose do neural networks serve for? Neural networks are learnable models. Their ultimate goal is to approach or even surpass human cognitive abilities. As Richard Sutton puts it, 'The biggest lesson that can be read from 70 years of AI research is that general methods that leverage computation are ultimately the most effective'. In his essay, Sutton argues that only models without encoded human-knowledge can outperform human-centeric approaches. Indeed, neural networks are general enough and they leverage computation.


Selected Publications

Early detection of malign patterns in patients’ biological signals can save millions of lives. Despite the steady improvement of artificial intelligence–based techniques, the practical clinical application of these methods is mostly constrained to an offline evaluation of the patients’ data. Previous studies have identified organic electrochemical devices as ideal candidates for biosignal monitoring. However, their use for pattern recognition in real time was never demonstrated. Here, we produce and characterize brain-inspired networks composed of organic electrochemical transistors and use them for time-series predictions and classification tasks using the reservoir computing approach. To show their potential use for biofluid monitoring and biosignal analysis, we classify four classes of arrhythmic heartbeats with an accuracy of 88%. The results of this study introduce a previously unexplored paradigm for biocompatible computational platforms and may enable development of ultralow–power consumption hardware-based artificial neural networks capable of interacting with body fluids and biological tissues.
Science Advances, 2021

Neural networks are currently transforming the field of computer algorithms, yet their emulation on current computing substrates is highly inefficient. Reservoir computing was successfully implemented on a large variety of substrates and gave new insight in overcoming this implementation bottleneck. Despite its success, the approach lags behind the state of the art in deep learning. We therefore extend time-delay reservoirs to deep networks and demonstrate that these conceptually correspond to deep convolutional neural networks. Convolution is intrinsically realized on a substrate level by generic drive-response properties of dynamical systems. The resulting novelty is avoiding vector-matrix products between layers, which cause low efficiency in today's substrates. Compared to singleton time-delay reservoirs, our deep network achieves accuracy improvements by at least an order of magnitude in Mackey-Glass and Lorenz timeseries prediction.
In PRL, 2019

Photonic delay systems have revolutionized the hardware implementation of Recurrent Neural Networks and Reservoir Computing in particular. The fundamental principles of Reservoir Computing strongly benefit a realization in such complex analog systems. Especially delay systems, potentially providing large numbers of degrees of freedom even in simple architectures, can efficiently be exploited for information processing. The numerous demonstrations of their performance led to a revival of photonic Artificial Neural Network. Today, an astonishing variety of physical substrates, implementation techniques as well as network architectures based on this approach have been successfully employed. Important fundamental aspects of analog hardware Artificial Neural Networks have been investigated, and multiple high-performance applications have been demonstrated. Here, we introduce and explain the most relevant aspects of Artificial Neural Networks and delay systems, the seminal experimental demonstrations of Reservoir Computing in photonic delay systems, plus and the most recent and advanced realizations.
JAP, 2018

We demonstrate for a nonlinear photonic system that two highly asymmetric feedback delays can induce a variety of emergent patterns which are highly robust during the system's global evolution. Explicitly, two-dimensional chimeras and dissipative solitons become visible upon a space-time transformation. Switching between chimeras and dissipative solitons requires only adjusting two system parameters, demonstrating self-organization exclusively based on the system's dynamical properties. Experiments were performed using a tunable semiconductor laser's transmission through a Fabry-Perot resonator resulting in an Airy function as nonlinearity. Resulting dynamics were band-pass filtered and propagated along two feedback paths whose time delays differ by two orders of magnitude. An excellent agreement between experimental results and theoretical model given by modified Ikeda equations was achieved.
Chaos, 2018

A chimera state is a rich and fascinating class of self-organized solutions developed in high-dimensional networks. Necessary features of the network for the emergence of such complex but structured motions are non-local and symmetry breaking coupling. An accurate understanding of chimera states is expected to bring important insights on deterministic mechanism occurring in many structurally similar high-dimensional dynamics such as living systems, brain operation principles and even turbulence in hydrodynamics. Here we report on a powerful and highly controllable experiment based on an optoelectronic delayed feedback applied to a wavelength tuneable semiconductor laser, with which a wide variety of chimera patterns can be accurately investigated and interpreted. We uncover a cascade of higher-order chimeras as a pattern transition from N to N+1 clusters of chaoticity. Finally, we follow visually, as the gain increases, how chimera state is gradually destroyed on the way to apparent turbulence-like system behaviour.
In Nat. Commun., 2015

Recent Publications

. Reservoir computing with biocompatible organic electrochemical networks for brain-inspired biosignal classification. Science Advances, 2021.

PDF Project Publication IEEE Spectrum

. In-Memory Resistive RAM Implementation of Binarized Neural Networks for Medical Applications. At DATE, 2020.

Preprint Project Publication

. Digital Biologically Plausible Implementation of Binarized Neural Networks with Differential Hafnium Oxide Resistive Memory Arrays. In Front. Neurosci., 2020.

Preprint PDF Project Project Publication

. Coupled Nonlinear Delay Systems As Deep Convolutional Neural Networks. In PRL, 2019.

Preprint Project Publication

. Stochastic Computing for Hardware Implementation of Binarized Neural Networks. IEEE Access, 2019.

Preprint PDF Project

. Efficient Design of Hardware-Enabled Reservoir Computing in FPGAs. JAP, 2018.


. Tutorial: Photonic Neural Networks in Delay Systems. JAP, 2018.

Project Publication

. Spatio-temporal complexity in dual delay nonlinear laser dynamics: chimeras and dissipative solitons. Chaos, 2018.

Preprint Project Project

. Laser chimeras as a paradigm for multistable patterns in complex systems. In Nat. Commun., 2015.

PDF Project

. Virtual Chimera States for Delayed-Feedback Systems. In PRL, 2013.

Preprint Project


Autonomous Factory

Autonomous molecule production factory powered by deep reinforcement learning.

Optical Proof of Work

Optical mining hardware targets to reduce electricity costs and waste heat with the help of integrated optical computing.

Energy-efficient AI

Bringing AI to the edge, to battery-powered devices and away from the cloud.

Syncronization patterns

Chimera states and dissipative soliton patterns for fast self-healing memory.

Bio-inspired computing

Conceiving next-generation computing principles inspired by biological systems such as the human brain.

Delay Differential Equations

A fast and flexible library solving delay differential equations.

Haskell MEP

Multi Expression Programming is a genetic programming variant encoding multiple solutions in the same chromosome. The remarkable thing about MEP algorithms is that they are programs actually writing programs.