Emre Neftci

Emre Neftci

Auto-generated profile, based on publicly available information

Emre Neftci

PGI-15, Forschungszentrum Jülich, Jülich, Germany

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

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

Representative Publications

View All Publications
1 November 2019 in IEEE Signal Processing Magazine
Verified
Journal Article
Closed access
ENEmre O. Neftci
Emre O. Neftci
HMHesham Mostafa
Hesham Mostafa
FZFriedemann Zenke
Friedemann Zenke

6 September 2023 in Proceedings of the IEEE
Verified
Journal Article
Open access
Jason K. EshraghianJason K. Eshraghian
Jason K. Eshraghian
MWMax Ward
Max Ward
ENEmre O. Neftci
Emre O. Neftci
XWXinxin Wang
Xinxin Wang
GLGregor Lenz
Gregor Lenz
WLWei Lu
Wei Lu
The brain is the perfect place to look for inspiration to develop more efficient neural networks. The inner workings of our synapses and neurons provide a glimpse at what the future of deep learning might look like. This article serves as a tutorial and perspective showing how to apply the lessons learned from several decades of research in deep learning, gradient descent, backpropagation, and neuroscience to biologically plausible spiking neural networks (SNNs). We also explore the delicate interplay between encoding data as spikes and the learning process; the challenges and solutions of applying gradient-based learning to SNNs; the subtle link between temporal backpropagation and spike timing-dependent plasticity; and how deep learning might move toward biologically plausible online learning. Some ideas are well accepted and commonly used among the neuromorphic engineering community, while others are presented or justified for the first time here. A series of companion interactive tutorials complementary to this article using our Python package, snnTorch , are also made available: https://snntorch.readthedocs.io/en/latest/tutorials/index.html.

12 May 2020 in Frontiers in Neuroscience
Verified
Journal Article
Open access
PDF file
JKJacques Kaiser
Jacques Kaiser
HMHesham Mostafa
Hesham Mostafa
ENEmre Neftci
Emre Neftci
A growing body of work underlines striking similarities between biological neural networks and recurrent, binary neural networks. A relatively smaller body of work, however, addresses the similarities between learning dynamics employed in deep artificial neural networks and synaptic plasticity in spiking neural networks. The challenge preventing this is largely caused by the discrepancy between the dynamical properties of synaptic plasticity and the requirements for gradient backpropagation. Learning algorithms that approximate gradient backpropagation using local error functions can overcome this challenge. Here, we introduce Deep Continuous Local Learning (DECOLLE), a spiking neural network equipped with local error functions for online learning with no memory overhead for computing gradients. DECOLLE is capable of learning deep spatio temporal representations from spikes relying solely on local information, making it compatible with neurobiology and neuromorphic hardware. Synaptic plasticity rules are derived systematically from user-defined cost functions and neural dynamics by leveraging existing autodifferentiation methods of machine learning frameworks. We benchmark our approach on the event-based neuromorphic dataset N-MNIST and DvsGesture, on which DECOLLE performs comparably to the state-of-the-art. DECOLLE networks provide continuously learning machines that are relevant to biology and supportive of event-based, low-power computer vision architectures matching the accuracies of conventional computers on tasks where temporal precision and speed are essential.

21 June 2017 in Frontiers in Neuroscience
Verified
Journal Article
Open access
ENEmre O. Neftci
Emre O. Neftci
CACharles Augustine
Charles Augustine
SPSomnath Paul
Somnath Paul
GDGeorgios Detorakis
Georgios Detorakis
An ongoing challenge in neuromorphic computing is to devise general and computationally efficient models of inference and learning which are compatible with the spatial and temporal constraints of the brain. One increasingly popular and successful approach is to take inspiration from inference and learning algorithms used in deep neural networks. However, the workhorse of deep learning, the gradient descent Back Propagation (BP) rule, often relies on the immediate availability of network-wide information stored with high-precision memory, and precise operations that are difficult to realize with spiking neurons. Remarkably, recent work showed that exact backpropagated weights are not essential for learning deep representations. Random BP replaces feedback weights with random ones and encourages the network to adjust its feed-forward weights to learn pseudo-inverses of the (random) feedback weights. Building on these results, we demonstrate an event-driven random BP (eRBP) rule that uses an error-modulated synaptic plasticity for learning deep representations in neuromorphic computing hardware. The rule involves only one addition and two comparisons for each synaptic weight using a two-compartment leaky Integrate & Fire (I&F) neuron, making it very suitable for implementation in digital or mixed-signal neuromorphic hardware. Our results show that using eRBP, deep representations are rapidly learned, achieving nearly identical classification accuracies compared to artificial neural network simulations on GPUs, while being robust to neural and synaptic state quantizations during learning.

1 January 2014 in Frontiers in Neuroscience
Verified
Journal Article
Open access
PDF file
ENEmre Neftci
Emre Neftci
SDSrinjoy Das
Srinjoy Das
BPBruno Pedroni
Bruno Pedroni
KKKenneth Kreutz-Delgado
Kenneth Kreutz-Delgado
GCGert Cauwenberghs
Gert Cauwenberghs
Restricted Boltzmann Machines (RBMs) and Deep Belief Networks have been demonstrated to perform efficiently in variety of applications, such as dimensionality reduction, feature learning, and classification. Their implementation on neuromorphic hardware platforms emulating large-scale networks of spiking neurons can have significant advantages from the perspectives of scalability, power dissipation and real-time interfacing with the environment. However the traditional RBM architecture and the commonly used training algorithm known as Contrastive Divergence (CD) are based on discrete updates and exact arithmetics which do not directly map onto a dynamical neural substrate. Here, we present an event-driven variation of CD to train a RBM constructed with Integrate & Fire (I&F) neurons, that is constrained by the limitations of existing and near future neuromorphic hardware platforms. Our strategy is based on neural sampling, which allows us to synthesize a spiking neural network that samples from a target Boltzmann distribution. The reverberating activity of the network replaces the discrete steps of the CD algorithm, while Spike Time Dependent Plasticity (STDP) carries out the weight updates in an online, asynchronous fashion.We demonstrate our approach by training an RBM composed of leaky I&F neurons with STDP synapses to learn a generative model of the MNIST hand-written digit dataset, and by testing it in recognition, generation and cue integration tasks. Our results contribute to a machine learning-driven approach for synthesizing networks of spiking neurons capable of carrying out practical, high-level functionality.

22 July 2013 in Proceedings of the National Academy of Sciences
Verified
Journal Article
Open access
PDF file
ENEmre Neftci
Emre Neftci
JBJonathan Binas
Jonathan Binas
URUeli Rutishauser
Ueli Rutishauser
ECElisabetta Chicca
Elisabetta Chicca
GIGiacomo Indiveri
Giacomo Indiveri
RDRodney J. Douglas
Rodney J. Douglas
Significance: Neuromorphic emulations express the dynamics of neural systems in analogous electronic circuits, offering a distributed, low-power technology for constructing intelligent systems. However, neuromorphic circuits are inherently imprecise and noisy, and there has been no systematic method for configuring reliable behavioral dynamics on these substrates. We describe such a method, which is able to install simple cognitive behavior on the neuromorphic substrate. Our approach casts light on the general question of how the neuronal circuits of the brain, and also future neuromorphic technologies, could implement cognitive behavior in a principled manner.