Cette dernière décennie a donné lieu à la réémergence des méthodes d'apprentissage machine basées sur les réseaux de neurones formels sous le nom d'apprentissage profond. Bien que ces méthodes aient permis des avancées majeures dans le domaine de l'apprentissage machine, plusieurs obstacles à la possibilité d'industrialiser ces méthodes persistent, notamment la nécessité de collecter et d'étiqueter une très grande quantité de données ainsi que la puissance de calcul nécessaire pour effectuer l'apprentissage et l'inférence avec ce type de réseau neuronal. Dans cette thèse, nous proposons d'étudier l'adéquation entre des algorithmes d'inférence et d'apprentissage issus des réseaux de neurones biologiques pour des architectures matérielles massivement parallèles. Nous montrons avec trois contributions que de telles adéquations permettent d'accélérer drastiquement les temps de calculs inhérents au réseaux de neurones. Dans notre premier axe, nous réalisons l'étude d'adéquation du moteur BCVision de Brainchip SAS pour les plate-formes GPU. Nous proposons également l'introduction d'une architecture hiérarchique basée sur des cellules complexes. Nous montrons que l'adéquation pour GPU accélère les traitements par un facteur sept, tandis que l'architecture hiérarchique atteint un facteur mille. La deuxième contribution présente trois algorithmes de propagation de décharges neuronales adaptés aux architectures parallèles. Nous réalisons une étude complète des modèles computationels de ces algorithmes, permettant de sélectionner ou de concevoir un système matériel adapté aux paramètres du réseau souhaité. Dans notre troisième axe nous présentons une méthode pour appliquer la règle Spike-Timing-Dependent-Plasticity à des données images afin d'apprendre de manière non-supervisée des représentations visuelles. Nous montrons que notre approche permet l'apprentissage d'une hiérarchie de représentations pertinente pour des problématiques de classification d'images, tout en nécessitant dix fois moins de données que les autres approches de la littérature. / The last decade has seen the re-emergence of machine learning methods based on formal neural networks under the name of deep learning. Although these methods have enabled a major breakthrough in machine learning, several obstacles to the possibility of industrializing these methods persist, notably the need to collect and label a very large amount of data as well as the computing power necessary to perform learning and inference with this type of neural network. In this thesis, we propose to study the adequacy between inference and learning algorithms derived from biological neural networks and massively parallel hardware architectures. We show with three contribution that such adequacy drastically accelerates computation times inherent to neural networks. In our first axis, we study the adequacy of the BCVision software engine developed by Brainchip SAS for GPU platforms. We also propose the introduction of a coarse-to-fine architecture based on complex cells. We show that GPU portage accelerates processing by a factor of seven, while the coarse-to-fine architecture reaches a factor of one thousand. The second contribution presents three algorithms for spike propagation adapted to parallel architectures. We study exhaustively the computational models of these algorithms, allowing the selection or design of the hardware system adapted to the parameters of the desired network. In our third axis we present a method to apply the Spike-Timing-Dependent-Plasticity rule to image data in order to learn visual representations in an unsupervised manner. We show that our approach allows the effective learning a hierarchy of representations relevant to image classification issues, while requiring ten times less data than other approaches in the literature.

Biological neural systems (BNS) in general and the central nervous system (CNS) specifically exhibit a strikingly efficient computational power along with an extreme flexible and adaptive basis for acquiring and integrating new knowledge. Acquiring more insights into the actual mechanisms of information processing within the BNS and their computational capabilities is a core objective of modern computer science, computational sciences and neuroscience. Among the main reasons of this tendency to understand the brain is to help in improving the quality of life of people suffer from loss (either partial or complete) of brain or spinal cord functions. Brain-computer-interfaces (BCI), neural prostheses and other similar approaches are potential solutions either to help these patients through therapy or to push the progress in rehabilitation. There is however a significant lack of knowledge regarding the basic information processing within the CNS. Without a better understanding of the fundamental operations or sequences leading to cognitive abilities, applications like BCI or neural prostheses will keep struggling to find a proper and systematic way to help patients in this regard. In order to have more insights into these basic information processing methods, this thesis presents an approach that makes a formal distinction between the essence of being intelligent (as for the brain) and the classical class of artificial intelligence, e.g. with expert systems. This approach investigates the underlying mechanisms allowing the CNS to be capable of performing a massive amount of computational tasks with a sustainable efficiency and flexibility. This is the essence of being intelligent, i.e. being able to learn, adapt and to invent. The approach used in the thesis at hands is based on the hypothesis that the brain or specifically a biological neural circuitry in the CNS is a dynamic system (network) that features emergent capabilities. These capabilities can be imported into spiking neural networks (SNN) by emulating the dynamic neural system. Emulating the dynamic system requires simulating both the inner workings of the system and the framework of performing the information processing tasks. Thus, this work comprises two main parts. The first part is concerned with introducing a proper and a novel dynamic synaptic model as a vital constitute of the inner workings of the dynamic neural system. This model represents a balanced integration between the needed biophysical details and being computationally inexpensive. Being a biophysical model is important to allow for the abilities of the target dynamic system to be inherited, and being simple is needed to allow for further implementation in large scale simulations and for hardware implementation in the future. Besides, the energy related aspects of synaptic dynamics are studied and linked to the behaviour of the networks seeking for stable states of activities. The second part of the thesis is consequently concerned with importing the processing framework of the dynamic system into the environment of SNN. This part of the study investigates the well established concept of binding by synchrony to solve the information binding problem and to proposes the concept of synchrony states within SNN. The concepts of computing with states are extended to investigate a computational model that is based on the finite-state machines and reservoir computing. Biological plausible validations of the introduced model and frameworks are performed. Results and discussions of these validations indicate that this study presents a significant advance on the way of empowering the knowledge about the mechanisms underpinning the computational power of CNS. Furthermore it shows a roadmap on how to adopt the biological computational capabilities in computation science in general and in biologically-inspired spiking neural networks in specific. Large scale simulations and the development of neuromorphic hardware are work-in-progress and future work. Among the applications of the introduced work are neural prostheses and bionic automation systems.

This paper introduces a new way of solving an edge user allocation problem. The problem is to be solved with a network of spiking neurons. This network should quickly and with low energy cost solve the optimization problem of allocating users to servers and minimizing the amount of servers hired to reduce the related hiring cost. The demonstrated method is a simulation of a method which could be implemented onto neuromorphic hardware. It is written in Python using the Brian2 spiking neural network simulator. The core of the method involves simulating an energy function through the use of circuit motifs. The dynamics of these circuit motifs mimic a search for the lowest energy point in an energy landscape, corresponding to a valid solution for the edge user allocation problem. The paper also shows the results of testing this network within the Brian2 environment.

The Chinese room argument (CRA) was first stated in 1980. Since then computer technologies have improved and today spiking neural networks (SNNs) are “arguably the only viable option if one wants to understand how the brain computes.” (Tavanei et.al. 2019: 47) SNNs differ in various important respects from the digital computers the CRA was directed against. The objective of the present work is to explore whether the CRA applies to SNNs. In the first chapter I am going to discuss computationalism, the Chinese room argument and give a brief overview over spiking neural networks. The second chapter is going to be considered with five important differences between SNNs and digital computers: (1) Massive parallelism, (2) subsymbolic computation, (3) machine learning, (4) analogue representation and (5) temporal encoding. I am going to finish by concluding that, besides minor limitations, the Chinese room argument can be applied to spiking neural networks.:1 Introduction 2 Theoretical background 2.I Strong AI: Computationalism 2.II The Chinese room argument 2.III Spiking neural networks 3 Applicability to spiking neural networks 3.I Massive parallelism 3.II Subsymbolic computation 3.III Machine learning 3.IV Analogue representation 3.V Temporal encoding 3.VI The Morse code room and its replies 3.VII Some more general considerations regarding hardware and software 4 Conclusion / Das Argument vom chinesischen Zimmer wurde erstmals 1980 veröffentlicht. Seit dieser Zeit hat sich die Computertechnologie stark weiterentwickelt und die heute viel beachteten gepulsten neuronalen Netze ähneln stark dem Aufbau und der Arbeitsweise biologischer Gehirne. Gepulste neuronale Netze unterscheiden sich in verschiedenen wichtigen Aspekten von den digitalen Computern, gegen die die CRA gerichtet war. Das Ziel der vorliegenden Arbeit ist es, zu untersuchen, ob das Argument vom chinesischen Zimmer auf gepulste neuronale Netze anwendbar ist. Im ersten Kapitel werde ich den Computer-Funktionalismus und das Argument des chinesischen Zimmers erörtern und einen kurzen Überblick über gepulste neuronale Netze geben. Das zweite Kapitel befasst sich mit fünf wichtigen Unterschieden zwischen gepulsten neuronalen Netzen und digitalen Computern: (1) Massive Parallelität, (2) subsymbolische Berechnung, (3) maschinelles Lernen, (4) analoge Darstellung und (5) zeitliche Kodierung. Ich werde schlussfolgern, dass das Argument des chinesischen Zimmers, abgesehen von geringfügigen Einschränkungen, auf gepulste neuronale Netze angewendet werden kann.:1 Introduction 2 Theoretical background 2.I Strong AI: Computationalism 2.II The Chinese room argument 2.III Spiking neural networks 3 Applicability to spiking neural networks 3.I Massive parallelism 3.II Subsymbolic computation 3.III Machine learning 3.IV Analogue representation 3.V Temporal encoding 3.VI The Morse code room and its replies 3.VII Some more general considerations regarding hardware and software 4 Conclusion

Cortical and subcortical microcircuits are continuously modified throughout life. Despite ongoing changes these networks stubbornly maintain their functions, which persist although destabilizing synaptic and nonsynaptic mechanisms should ostensibly propel them towards runaway excitation or quiescence. What dynamical phenomena exist to act together to balance such learning with information processing? What types of activity patterns do they underpin, and how do these patterns relate to our perceptual experiences? What enables learning and memory operations to occur despite such massive and constant neural reorganization? Progress towards answering many of these questions can be pursued through large-scale neuronal simulations.    In this thesis, a Hebbian learning rule for spiking neurons inspired by statistical inference is introduced. The spike-based version of the Bayesian Confidence Propagation Neural Network (BCPNN) learning rule involves changes in both synaptic strengths and intrinsic neuronal currents. The model is motivated by molecular cascades whose functional outcomes are mapped onto biological mechanisms such as Hebbian and homeostatic plasticity, neuromodulation, and intrinsic excitability. Temporally interacting memory traces enable spike-timing dependence, a stable learning regime that remains competitive, postsynaptic activity regulation, spike-based reinforcement learning and intrinsic graded persistent firing levels.    The thesis seeks to demonstrate how multiple interacting plasticity mechanisms can coordinate reinforcement, auto- and hetero-associative learning within large-scale, spiking, plastic neuronal networks. Spiking neural networks can represent information in the form of probability distributions, and a biophysical realization of Bayesian computation can help reconcile disparate experimental observations. / <p>QC 20170421</p>

A ideia de usar redes neurais biologicamente inspiradas na computação tem sido amplamente utilizada nas últimas décadas. O fato essencial neste paradigma é que um neurônio pode integrar e processar informações, e esta informação pode ser revelada por sua atividade de pulsos. Ao descrever a dinâmica de um único neurônio usando um modelo matemático, uma rede pode ser implementada utilizando um conjunto desses neurônios, onde a atividade pulsante de cada neurônio irá conter contribuições, ou informações, da atividade pulsante da rede em que está inserido. Neste trabalho é apresentado um controlador de posição no eixo Z utilizando fusão de sensores baseado no paradigma de Redes Neurais Recorrentes. O sistema proposto utiliza uma Máquina de Estado Líquido (LSM) para controlar o robô colaborativo BAXTER. O framework foi projetado para trabalhar em paralelo com as LSMs que executam trajetórias em formas fechadas de duas dimensões, com o objetivo de manter uma caneta de feltro em contato com a superfície de desenho, dados de sensores de força e distância são alimentados ao controlador. O sistema foi treinado utilizando dados de um controlador Proporcional Integral Derivativo (PID), fundindo dados de ambos sensores. Resultados mostram que a LSM foi capaz de aprender o comportamento do controlador PID em diferentes situações. / The idea of employing biologically inspired neural networks to perform computation has been widely used over the last decades. The essential fact in this paradigm is that a neuron can integrate and process information, and this information can be revealed by its spiking activity. By describing the dynamics of a single neuron using a mathematical model, a network in which the spiking activity of every single neuron will get contributions, or information, from the spiking activity of the embedded network. A positioning controller based on Spiking Neural Networks for sensor fusion suitable to run on a neuromorphic computer is presented in this work. The proposed framework uses the paradigm of reservoir computing to control the collaborative robot BAXTER. The system was designed to work in parallel with Liquid State Machines that performs trajectories in 2D closed shapes. In order to keep a felt pen touching a drawing surface, data from sensors of force and distance are fed to the controller. The system was trained using data from a Proportional Integral Derivative controller, merging the data from both sensors. The results show that the LSM can learn the behavior of a PID controller on di erent situations.

En utilisant les méthodes d’apprentissages tirées des récentes découvertes en neuroscience, les réseaux de neurones impulsionnels ont démontrés leurs capacités à analyser efficacement les grandes quantités d’informations provenant de notre environnement. L’implémentation de ces circuits à l’aide de processeurs classiques ne permet pas d’exploiter efficacement leur parallélisme. L’utilisation de mémoire numérique pour implémenter les poids synaptique ne permet pas la lecture ou la programmation parallèle des synapses et est limité par la bande passante reliant la mémoire à l’unité de calcul. Les technologies mémoire de type memristive pourrait permettre l’implémentation de ce parallélisme au coeur de la mémoire.Dans cette thèse, nous envisageons le développement d’un réseau de neurones impulsionnels dédié au monde de l’embarqué à base de dispositif mémoire émergents. Dans un premier temps, nous avons analysé un réseau impulsionnel afin d’optimiser ses différentes composantes : neurone, synapse et méthode d’apprentissage STDP en vue d’une implémentation numérique. Dans un second temps, nous envisageons l’implémentation de la mémoire synaptique par des dispositifs memristifs. Enfin, nous présentons le développement d’une puce co-intégrant des neurones implémentés en CMOS avec des synapses en technologie CBRAM. / By using learning mechanisms extracted from recent discoveries in neuroscience, spiking neural networks have demonstrated their ability to efficiently analyze the large amount of data from our environment. The implementation of such circuits on conventional processors does not allow the efficient exploitation of their parallelism. The use of digital memory to implement the synaptic weight does not allow the parallel reading or the parallel programming of the synapses and it is limited by the bandwidth of the connection between the memory and the processing unit. Emergent memristive memory technologies could allow implementing this parallelism directly in the heart of the memory.In this thesis, we consider the development of an embedded spiking neural network based on emerging memory devices. First, we analyze a spiking network to optimize its different components: the neuron, the synapse and the STDP learning mechanism for digital implementation. Then, we consider implementing the synaptic memory with emergent memristive devices. Finally, we present the development of a neuromorphic chip co-integrating CMOS neurons with CBRAM synapses.

Um dos grandes mistérios da ciência é compreender como sistemas nervosos são capazes de realizar as extraordinárias operações computacionais que realizam. Provavelmente, encéfalos são as estruturas nas quais energia e matéria estão organizadas da forma mais complexa no universo. Central na computação cerebral está o conceito de neurônio. A forma como neurônios computam é motivo de intensa investigação científica. Um consenso atual é que neurônios formam grupos transientes (assembleias) a fim de representar coisas, de realizar operações computacionais, e de executar processos cognitivos; embora os mecanismos que fundamentam a computação por assembleias ainda não seja bem compreendido. Aqui é proposta uma forma pela qual se explica como computação por assembleias pode acontecer. Dois componentes são fundamentais para formação de coalizões neurais: a relação temporal entre grupos de neurônios e o fator de acoplamento entre eles. Assembleias pressupõe neurônios pulsantes; portanto, simulamos computação por assembleias em redes neurais pulsantes. A abordagem usada nesta tese é funcional; apresentamos um arcabouço teórico sobre propriedades, princípios, e dinâmicas que permitem operações computacionais por coalizões neurais. É apresentado na tese que: (i) quando neurônios formam assembleias está implícito que um tipo de função lógica estocástica ocorre, (ii) assembleias podem formar grupos com feedback, criando grupos biestáveis, (iii) grupos biestáveis criam representações internas dos eventos que os criaram, (iv) assembleias podem se ramificar e também dissolver outras assembleias, o que dá origem a algoritmos complexos. Esta é uma investigação inicial sobre computação em assembleias neurais, e há muito a ser feito. Nesta tese apresentamos os conceitos basais para esta nova abordagem. Há um conjunto de programas nos apêndices que permitem ao leitor simular formações de assembleias, ramificações, inibições, reverberações, entre outras propriedades e componentes de nossa proposta. / One of the greatest mysteries in science is to comprehend how brains are capable of realizing the extraordinary computational operations they do. Probably, brains are the structures in which matter and energy are organized in the most complex way in the Universe. Central to the brain computation is the concept of neuron. How neurons compute is motive of intensive scientific investigation. A prevailing consensus is that neurons form transient groups (assemblies) in order to represent things, for realizing computational operations, and for executing cognitive processes; although the mechanisms that substantiate such computation by neural assemblies are not yet well understood. In this thesis we propose a form that explains how neural assembly computation may occur. It is shown that two components are fundamentals for neural coalition formation: the temporal relation among neural groups, and the coupling factor among them. In this sense, neural assemblies presuppose spiking neurons; therefore, here we simulate assembly computing using spiking neural networks. In this thesis it is presented basically a functional approach; thus, it presents a theoretical approach concerning the properties, principles, characteristics, and components that allow the computational operations in neural coalitions. It is presented in the thesis that: (i) as neurons form assemblies it is implicit that a kind of stochastic logic function occurs; (ii) assemblies may form groups that feedback each other, creating bistable groups; (iii) bistable groups internally represent the event that created them; (iv) assemblies may branch and dissolve other assemblies, what give rise to complex algorithms. This is an initial investigation about neural assembly computing and there is a lot to be done; however, in this thesis we present the basal concepts for this new approach. There are programs in the appendices that allow the reader to simulate assembly formation, branching, inhibition, reverberation, among other properties and components in our proposal.

Um dos grandes mistérios da ciência é compreender como sistemas nervosos são capazes de realizar as extraordinárias operações computacionais que realizam. Provavelmente, encéfalos são as estruturas nas quais energia e matéria estão organizadas da forma mais complexa no universo. Central na computação cerebral está o conceito de neurônio. A forma como neurônios computam é motivo de intensa investigação científica. Um consenso atual é que neurônios formam grupos transientes (assembleias) a fim de representar coisas, de realizar operações computacionais, e de executar processos cognitivos; embora os mecanismos que fundamentam a computação por assembleias ainda não seja bem compreendido. Aqui é proposta uma forma pela qual se explica como computação por assembleias pode acontecer. Dois componentes são fundamentais para formação de coalizões neurais: a relação temporal entre grupos de neurônios e o fator de acoplamento entre eles. Assembleias pressupõe neurônios pulsantes; portanto, simulamos computação por assembleias em redes neurais pulsantes. A abordagem usada nesta tese é funcional; apresentamos um arcabouço teórico sobre propriedades, princípios, e dinâmicas que permitem operações computacionais por coalizões neurais. É apresentado na tese que: (i) quando neurônios formam assembleias está implícito que um tipo de função lógica estocástica ocorre, (ii) assembleias podem formar grupos com feedback, criando grupos biestáveis, (iii) grupos biestáveis criam representações internas dos eventos que os criaram, (iv) assembleias podem se ramificar e também dissolver outras assembleias, o que dá origem a algoritmos complexos. Esta é uma investigação inicial sobre computação em assembleias neurais, e há muito a ser feito. Nesta tese apresentamos os conceitos basais para esta nova abordagem. Há um conjunto de programas nos apêndices que permitem ao leitor simular formações de assembleias, ramificações, inibições, reverberações, entre outras propriedades e componentes de nossa proposta. / One of the greatest mysteries in science is to comprehend how brains are capable of realizing the extraordinary computational operations they do. Probably, brains are the structures in which matter and energy are organized in the most complex way in the Universe. Central to the brain computation is the concept of neuron. How neurons compute is motive of intensive scientific investigation. A prevailing consensus is that neurons form transient groups (assemblies) in order to represent things, for realizing computational operations, and for executing cognitive processes; although the mechanisms that substantiate such computation by neural assemblies are not yet well understood. In this thesis we propose a form that explains how neural assembly computation may occur. It is shown that two components are fundamentals for neural coalition formation: the temporal relation among neural groups, and the coupling factor among them. In this sense, neural assemblies presuppose spiking neurons; therefore, here we simulate assembly computing using spiking neural networks. In this thesis it is presented basically a functional approach; thus, it presents a theoretical approach concerning the properties, principles, characteristics, and components that allow the computational operations in neural coalitions. It is presented in the thesis that: (i) as neurons form assemblies it is implicit that a kind of stochastic logic function occurs; (ii) assemblies may form groups that feedback each other, creating bistable groups; (iii) bistable groups internally represent the event that created them; (iv) assemblies may branch and dissolve other assemblies, what give rise to complex algorithms. This is an initial investigation about neural assembly computing and there is a lot to be done; however, in this thesis we present the basal concepts for this new approach. There are programs in the appendices that allow the reader to simulate assembly formation, branching, inhibition, reverberation, among other properties and components in our proposal.

Health monitoring devices, such as Fitbit, are gaining popularity both as wellness tools and as a source of information for healthcare decisions. Predicting such wellness goals accurately is critical for the users to make informed lifestyle choices. The core objective of this thesis is to design and implement such a system that takes energy consumption and privacy into account. This research is modelled as a time-series forecasting problem that makes use of Spiking Neural Networks (SNNs) due to their proven energy-saving capabilities. Thanks to their design that closely mimics natural neural networks (such as the brain), SNNs have the potential to significantly outperform classic Artificial Neural Networks in terms of energy consumption and robustness. In order to prove our hypotheses, a previous research by Sonia et al. [1] in the same domain and with the same dataset is used as our starting point, where a private forecasting system using Long short-term memory (LSTM) is designed and implemented. Their study also implements and evaluates a clustering federated learning approach, which fits well the highly distributed data. The results obtained in their research act as a baseline to compare our results in terms of accuracy, training time, model size and estimated energy consumed. Our experiments show that Spiking Neural Networks trades off accuracy (2.19x, 1.19x, 4.13x, 1.16x greater Root Mean Square Error (RMSE) for macronutrients, calories burned, resting heart rate, and active minutes respectively), to grant a smaller model (19% less parameters an 77% lighter in memory) and a 43% faster training. Our model is estimated to consume 3.36μJ per inference, which is much lighter than traditional Artificial Neural Networks (ANNs) [2]. The data recorded by health monitoring devices is vastly distributed in the real-world. Moreover, with such sensitive recorded information, there are many possible implications to consider. For these reasons, we apply the clustering federated learning implementation [1] to our use-case. However, it can be challenging to adopt such techniques since it can be difficult to learn from data sequences that are non-regular. We use a two-step streaming clustering approach to classify customers based on their eating and exercise habits. It has been shown that training different models for each group of users is useful, particularly in terms of training time; however this is strongly dependent on the cluster size. Our experiments conclude that there is a decrease in error and training time if the clusters contain enough data to train the models. Finally, this study addresses the issue of data privacy by using state of-the-art differential privacy. We apply e-differential privacy to both our baseline model (trained on the whole dataset) and our federated learning based approach. With a differential privacy of ∈= 0.1 our experiments report an increase in the measured average error (RMSE) of only 25%. Specifically, +23.13%, 25.71%, +29.87%, 21.57% for macronutrients (grams), calories burned (kCal), resting heart rate (beats per minute (bpm), and minutes (minutes) respectively. / Hälsoövervakningsenheter, som Fitbit, blir allt populärare både som friskvårdsverktyg och som informationskälla för vårdbeslut. Att förutsäga sådana välbefinnandemål korrekt är avgörande för att användarna ska kunna göra välgrundade livsstilsval. Kärnmålet med denna avhandling är att designa och implementera ett sådant system som tar hänsyn till energiförbrukning och integritet. Denna forskning är modellerad som ett tidsserieprognosproblem som använder sig av SNNs på grund av deras bevisade energibesparingsförmåga. Tack vare deras design som nära efterliknar naturliga neurala nätverk (som hjärnan) har SNNs potentialen att avsevärt överträffa klassiska artificiella neurala nätverk när det gäller energiförbrukning och robusthet. För att bevisa våra hypoteser har en tidigare forskning av Sonia et al. [1] i samma domän och med samma dataset används som utgångspunkt, där ett privat prognossystem som använder LSTM designas och implementeras. Deras studie implementerar och utvärderar också en klustringsstrategi för federerad inlärning, som passar väl in på den mycket distribuerade data. Resultaten som erhållits i deras forskning fungerar som en baslinje för att jämföra våra resultat vad gäller noggrannhet, träningstid, modellstorlek och uppskattad energiförbrukning. Våra experiment visar att Spiking Neural Networks byter ut precision (2,19x, 1,19x, 4,13x, 1,16x större RMSE för makronäringsämnen, förbrända kalorier, vilopuls respektive aktiva minuter), för att ge en mindre modell ( 19% mindre parametrar, 77% lättare i minnet) och 43% snabbare träning. Vår modell beräknas förbruka 3, 36μJ, vilket är mycket lättare än traditionella ANNs [2]. Data som registreras av hälsoövervakningsenheter är enormt spridda i den verkliga världen. Dessutom, med sådan känslig registrerad information finns det många möjliga konsekvenser att överväga. Av dessa skäl tillämpar vi klustringsimplementeringen för federerad inlärning [1] på vårt användningsfall. Det kan dock vara utmanande att använda sådana tekniker eftersom det kan vara svårt att lära sig av datasekvenser som är oregelbundna. Vi använder en tvåstegs streaming-klustringsmetod för att klassificera kunder baserat på deras mat- och träningsvanor. Det har visat sig att det är användbart att träna olika modeller för varje grupp av användare, särskilt när det gäller utbildningstid; detta är dock starkt beroende av klustrets storlek. Våra experiment drar slutsatsen att det finns en minskning av fel och träningstid om klustren innehåller tillräckligt med data för att träna modellerna. Slutligen tar denna studie upp frågan om datasekretess genom att använda den senaste differentiell integritet. Vi tillämpar e-differentiell integritet på både vår baslinjemodell (utbildad på hela datasetet) och vår federerade inlärningsbaserade metod. Med en differentiell integritet på ∈= 0.1 rapporterar våra experiment en ökning av det uppmätta medelfelet (RMSE) på endast 25%. Specifikt +23,13%, 25,71%, +29,87%, 21,57% för makronäringsämnen (gram), förbrända kalorier (kCal), vilopuls (bpm och minuter (minuter).