Pos	Paper	Citations	Year
1	Real-time computing without stable states: A new framework for neural computation based on perturbations	5488	2002
2	Networks of spiking neurons: the third generation of neural network models	5226	1997
3	Pulsed neural networks	1393	2001
4	State-dependent computations: spatiotemporal processing in cortical networks	1202	2009
5	Approximation schemes for covering and packing problems in image processing and VLSI	1016	1985
6	A solution to the learning dilemma for recurrent networks of spiking neurons	797	2020
7	Long short-term memory and learning-to-learn in networks of spiking neurons	765	2018
8	2022 roadmap on neuromorphic computing and engineering	734	2022
9	On the computational power of circuits of spiking neurons	728	2004
10	Edge of chaos and prediction of computational performance for neural circuit models	646	2007
11	Neural dynamics as sampling: a model for stochastic computation in recurrent networks of spiking neurons	569	2011
12	Threshold circuits of bounded depth	523	1993
13	On the computational power of winner-take-all	485	2000
14	Towards a theoretical foundation for morphological computation with compliant bodies	475	2011
15	Deep rewiring: Training very sparse deep networks	403	2017
16	Lower bounds for the computational power of networks of spiking neurons	392	1996
17	A learning theory for reward-modulated spike-timing-dependent plasticity with application to biofeedback	369	2008
18	Bayesian computation emerges in generic cortical microcircuits through spike-timing-dependent plasticity	369	2013
19	Liquid state machines: motivation, theory, and applications	338	2011
20	The" liquid computer": A novel strategy for real-time computing on time series	338	2011
21	Computational aspects of feedback in neural circuits	323	2007
22	Fast sigmoidal networks via spiking neurons	310	1997
23	A statistical analysis of information-processing properties of lamina-specific cortical microcircuit models	305	2007
24	What can a neuron learn with spike-timing-dependent plasticity?	299	2005
25	On the computational power of noisy spiking neurons	291	1995
26	Inferring spike trains from local field potentials	287	2008
27	Computational models for generic cortical microcircuits	277	2004
28	Noise as a resource for computation and learning in networks of spiking neurons	272	2014
29	A learning rule for very simple universal approximators consisting of a single layer of perceptrons	266	2008
30	Neuromorphic hardware in the loop: Training a deep spiking network on the brainscales wafer-scale system	248	2017
31	A pulse-coded communications infrastructure for neuromorphic systems	237	1999
32	Distributed fading memory for stimulus properties in the primary visual cortex	229	2009
33	Special issue on echo state networks and liquid state machines	222	2007
34	Optimized spiking neurons can classify images with high accuracy through temporal coding with two spikes	218	2021
35	Dynamic stochastic synapses as computational units	216	1997
36	Branch-specific plasticity enables self-organization of nonlinear computation in single neurons	201	2011
37	Emergence of complex computational structures from chaotic neural networks through reward-modulated Hebbian learning	191	2014
38	Theory and applications of agnostic PAC-learning with small decision trees	182	1995
39	A reward-modulated hebbian learning rule can explain experimentally observed network reorganization in a brain control task	175	2010
40	What makes a dynamical system computationally powerful	175	2007
41	A long short-term memory for AI applications in spike-based neuromorphic hardware	172	2022
42	Network plasticity as Bayesian inference	166	2015
43	The role of feedback in morphological computation with compliant bodies	165	2012
44	STDP enables spiking neurons to detect hidden causes of their inputs	162	2009
45	Brain computation by assemblies of neurons	155	2020
46	Probabilistic inference in general graphical models through sampling in stochastic networks of spiking neurons	155	2011
47	Bounds for the computational power and learning complexity of analog neural nets	148	1993
48	A model for real-time computation in generic neural microcircuits	147	2002
49	On the computational power of sigmoid versus boolean threshold circuits	147	1991
50	STDP installs in winner-take-all circuits an online approximation to hidden Markov model learning	147	2014
51	Vapnik-Chervonenkis dimension of neural nets	147	2003
52	On the effect of analog noise in discrete-time analog computations	138	1998
53	Biologically inspired alternatives to backpropagation through time for learning in recurrent neural nets	132	2019
54	Synapses as dynamic memory buffers	131	2002
55	Fading memory and kernel properties of generic cortical microcircuit models	127	2004
56	How fast can a threshold gate learn?	125	1994
57	Movement generation with circuits of spiking neurons	124	2005
58	Brain-inspired computing: A systematic survey and future trends	123	2024
59	Emergence of dynamic memory traces in cortical microcircuit models through STDP	116	2013
60	Stochastic computations in cortical microcircuit models	115	2013
61	Efficient agnostic pac-learning with simple hypothesis	112	1994
62	Networks of spiking neurons can emulate arbitrary Hopfield nets in temporal coding	112	1997
63	Visualizing a joint future of neuroscience and neuromorphic engineering	112	2021
64	Lower bound methods and separation results for on-line learning models	111	1992
65	Spike frequency adaptation supports network computations on temporally dispersed information	111	2021
66	On the complexity of learning for spiking neurons with temporal coding	108	1999
67	Neural systems as nonlinear filters	107	2000
68	Neural nets with superlinear VC-dimension	106	1994
69	Computer models and analysis tools for neural microcircuits	102	2003
70	Solving constraint satisfaction problems with networks of spiking neurons	102	2016
71	On the communication complexity of graph properties	100	1988
72	Analog neural nets with gaussian or other common noise distributions cannot recognize arbitrary regular languages	95	1999
73	Efficient temporal processing with biologically realistic dynamic synapses	92	2001
74	On the computational complexity of networks of spiking neurons	91	1994
75	To spike or not to spike: that is the question	91	2015
76	Memory-efficient deep learning on a SpiNNaker 2 prototype	90	2018
77	On the complexity of learning from counterexamples	89	1989
78	Efficient learning with virtual threshold gates	86	1998
79	On the computational power of circuits of spiking neurons	86	2004
80	Computing the maximum bichromatic discrepancy, with applications to computer graphics and machine learning	85	1996
81	Coding and learning of behavioral sequences	83	2004
82	Oracle-dependent properties of the lattice of NP sets	82	1983
83	Temporal dynamics of information content carried by neurons in the primary visual cortex	81	2006
84	Belief propagation in networks of spiking neurons	77	2009
85	A new approach towards vision suggested by biologically realistic neural microcircuit models	76	2002
86	Movement generation and control with generic neural microcircuits	75	2004
87	Neural computation with winner-take-all as the only nonlinear operation	75	1999
88	Recursively enumerable generic sets	75	1982
89	Fast approximation algorithms for a nonconvex covering problem	74	1987
90	Motion planning among time dependent obstacles	73	1988
91	Spiking neurons and the induction of finite state machines	73	2002
92	Ensembles of spiking neurons with noise support optimal probabilistic inference in a dynamically changing environment	70	2014
93	Neuromorphic hardware learns to learn	70	2019
94	Searching for principles of brain computation	70	2016
95	A dynamic connectome supports the emergence of stable computational function of neural circuits through reward-based learning	69	2018
96	Paradigms for computing with spiking neurons	67	2002
97	Methods for estimating the computational power and generalization capability of neural microcircuits	65	2004
98	Combinatorial lower bound arguments for deterministic and nondeterministic Turing machines	64	1985
99	Efficient reward-based structural plasticity on a SpiNNaker 2 prototype	64	2019
100	Pulsed neural networks	64	1999
101	Reducing communication for distributed learning in neural networks	64	2002
102	Vapnik-Chervonenkis dimension of neural nets	64	1995
103	Learned graphical models for probabilistic planning provide a new class of movement primitives	63	2013
104	Meanders, Ramsey theory and lower bounds for branching programs	63	1986
105	A data-based large-scale model for primary visual cortex enables brain-like robust and versatile visual processing	61	2022
106	Learning complex motions by sequencing simpler motion templates	61	2009
107	Self-tuning of neural circuits through short-term synaptic plasticity	61	2007
108	Liquid computing	60	2007
109	12 Computing and Learning with Dynamic Synapses	57	2007
110	Motif distribution, dynamical properties, and computational performance of two data-based cortical microcircuit templates	56	2009
111	On-line learning of rectangles	56	1992
112	On the complexity of learning from counterexamples and membership queries	56	1990
113	Algorithms and lower bounds for on-line learning of geometrical concepts	54	1994
114	Principles of real-time computing with feedback applied to cortical microcircuit models	54	2005
115	A quantitative analysis of information about past and present stimuli encoded by spikes of A1 neurons	53	2012
116	Input prediction and autonomous movement analysis in recurrent circuits of spiking neurons	53	2003
117	On the computational power of threshold circuits with sparse activity	48	2006
118	Quadratic lower bounds for deterministic and nondeterministic one-tape Turing machines	48	1984
119	Splitting properties and jump classes	46	1981
120	On the relevance of time in neural computation and learning	45	2001
121	Reward-modulated Hebbian learning of decision making	45	2010
122	Emergence of optimal decoding of population codes through STDP	44	2013
123	Perspectives of current research about the complexity of learning on neural nets	43	1994
124	On the complexity of learning for a spiking neuron	42	1997
125	Biologically inspired kinematic synergies enable linear balance control of a humanoid robot	41	2011
126	Characterization of recursively enumerable sets with supersets effectively isomorphic to all recursively enumerable sets	40	1983
127	A simple model for Behavioral Time Scale Synaptic Plasticity (BTSP) provides content addressable memory with binary synapses and one-shot learning	39	2025
128	A comparison of the computational power of sigmoid and Boolean threshold circuits	38	1994
129	A model for fast analog computation based on unreliable synapses	38	2000
130	Perspectives of the high‐dimensional dynamics of neural microcircuits from the point of view of low‐dimensional readouts	37	2003
131	Spiking neurons can learn to solve information bottleneck problems and extract independent components	37	2009
132	Statistical comparison of spike responses to natural stimuli in monkey area V1 with simulated responses of a detailed laminar network model for a patch of V1	37	2011
133	Agnostic PAC-learning of functions on analog neural nets	36	1993
134	A spiking neuron as information bottleneck	36	2010
135	Biologically inspired kinematic synergies provide a new paradigm for balance control of humanoid robots	35	2007
136	Long term memory and the densest k-subgraph problem	34	2018
137	Reservoirs learn to learn	33	2021
138	The intervals of the lattice of recursively enumerable sets determined by major subsets	33	1983
139	Compensating inhomogeneities of neuromorphic VLSI devices via short-term synaptic plasticity	32	2010
140	Feedback inhibition shapes emergent computational properties of cortical microcircuit motifs	32	2017
141	On the complexity of function learning	32	1993
142	Synaptic sampling: A Bayesian approach to neural network plasticity and rewiring	32	2015
143	Local prediction-learning in high-dimensional spaces enables neural networks to plan	31	2024
144	On-line learning with an oblivious environment and the power of randomization	31	1991
145	Brain computation: a computer science perspective	30	2019
146	Distributed bayesian computation and self-organized learning in sheets of spiking neurons with local lateral inhibition	30	2015
147	Theory of the computational function of microcircuit dynamics	30	2006
148	A fresh look at real-time computation in generic recurrent neural circuits	29	2002
149	Replacing supervised classification learning by Slow Feature Analysis in spiking neural networks	29	2009
150	STDP forms associations between memory traces in networks of spiking neurons	29	2020
151	Neuromorphic hardware for sustainable AI data centers	28	2024
152	Inadmissibility, tame re sets and the admissible collapse	27	1978
153	One-shot learning with spiking neural networks	27	2020
154	On the relevance of time in neural computation and learning	27	1997
155	Brain inspired computing: A systematic survey and future trends	26	2023
156	On computation with pulses	26	1999
157	Pattern representation and recognition with accelerated analog neuromorphic systems	24	2017
158	Two tapes versus one for off-line Turing machines	24	1993
159	Approximation schemes for covering and packing problems in robotics and vlsi	23	1984
160	Liquid computing in a simplified model of cortical layer IV: learning to balance a ball	23	2012
161	Motivation, theory, and applications of liquid state machines	23	2011
162	Simplified rules and theoretical analysis for information bottleneck optimization and PCA with spiking neurons	23	2007
163	Computing the optimally fitted spike train for a synapse	22	2001
164	A theoretical basis for emergent pattern discrimination in neural systems through slow feature extraction	21	2010
165	Efficient continuous-time reinforcement learning with adaptive state graphs	21	2007
166	Energy-efficient neural network chips approach human recognition capabilities	21	2016
167	Hebbian learning of Bayes optimal decisions	21	2008
168	Introduction: Spiking neurons in neuroscience and technology	21	2001
169	On the orbits of hyperhypersimple sets	21	1984
170	Smoothed analysis of discrete tensor decomposition and assemblies of neurons	21	2018
171	Speed-up of Turing machines with one work tape and a two-way input tape	21	1987
172	Associative memory with networks of spiking neurons in temporal coding	19	1998
173	Embodied synaptic plasticity with online reinforcement learning	19	2019
174	Foundations for a circuit complexity theory of sensory processing	19	2000
175	Information dynamics and emergent computation in recurrent circuits of spiking neurons	19	2003
176	Learning probabilistic inference through spike-timing-dependent plasticity	19	2016
177	On the classification capability of sign-constrained perceptrons	19	2008
178	The complexity of matrix transposition on one-tape off-line Turing machines	19	1991
179	Two tapes are better than one for off-line Turing machines	19	1987
180	On learnability and predicate logic	18	1995
181	Pulsed neural networks	18	1999
182	The p-delta learning rule for parallel perceptrons	18	2001
183	A simple model for neural computation with firing rates and firing correlations	17	1998
184	Fast identification of geometric objects with membership queries	17	1991
185	Recognizing images with at most one spike per neuron	17	1995
186	Theoretical analysis of learning with reward-modulated spike-timing-dependent plasticity	17	2007
187	Neural circuits for pattern recognition with small total wire length	16	2002
188	On the role of time and space in neural computation	16	1998
189	Temporal integration in recurrent microcircuits	16	2003
190	An efficient implementation of sigmoidal neural nets in temporal coding with noisy spiking neurons	15	1995
191	Finding the Key to a Synapse	15	2000
192	Lower bound arguments with “inaccessible” numbers	15	1988
193	An optimal lower bound for Turing machines with one work tape and a two-way input tape	14	2005
194	Assembly pointers for variable binding in networks of spiking neurons	14	2024
195	Dynamics of information and emergent computation in generic neural microcircuit models	14	2005
196	Emulation of Hopfield networks with spiking neurons in temporal coding	14	1998
197	Fast learning without synaptic plasticity in spiking neural networks	14	2024
198	Information bottleneck optimization and independent component extraction with spiking neurons	14	2006
199	Learning of depth two neural networks with constant fan-in at the hidden nodes	14	1996
200	On minimal pairs and minimal degrees in higher recursion theory	14	1977
201	On the complexity of nonconvex covering	14	1986
202	Probing real sensory worlds of receivers with unsupervised clustering	14	2012
203	A model for structured information representation in neural networks of the brain	13	2020
204	Current state and future directions for learning in biological recurrent neural networks: A perspective piece	13	2021
205	Eligibility traces provide a data-inspired alternative to backpropagation through time	13	2019
206	Fast identification of geometric objects with membership queries	13	1995
207	Functional network reorganization in motor cortex can be explained by reward-modulated Hebbian learning	13	2009
208	A probabilistic model for learning in cortical microcircuit motifs with data-based divisive inhibition	12	2017
209	Classifying images with few spikes per neuron	12	2020
210	Group Report: Neocortical Microcircuits—UPs and DOWNs in Cortical Computation	12	2017
211	Spike-frequency adaptation provides a long short-term memory to networks of spiking neurons	12	2020
212	Structure induces computational function in networks with diverse types of spiking neurons	12	2021
213	Fast analog computation in networks of spiking neurons using unreliable synapses	11	1999
214	Reward-based stochastic self-configuration of neural circuits	11	2017
215	Ups and downs in the genesis of cortical computation	11	2006
216	Probabilistic skeletons endow brain-like neural networks with innate computing capabilities	10	2021
217	A criterion for the convergence of learning with spike timing dependent plasticity	9	2005
218	Analog computations on networks of spiking neurons	9	1995
219	Are recursion theoretic arguments useful in complexity theory?	9	1986
220	CaMKII activation supports reward-based neural network optimization through Hamiltonian sampling	9	2016
221	On the use of inaccessible numbers and order indiscernibles in lower bound arguments for random access machines	9	1988
222	Towards a computational semantics of path relations	9	1997
223	A model for the interaction of oscillations and pattern generation with real-time computing in generic neural microcircuit models	8	2006
224	Contributions to [alpha]-and [beta]-recursion Theory	8	1993
225	Neural computation: a research topic for theoretical computer science? Some thoughts and pointers	8	2001
226	On the complexity of learning on feedforward neural nets	8	1993
227	On the complexity of learning on neural nets	8	1994
228	The computational power of spiking neurons depends on the shape of the postsynaptic potentials	8	1996
229	Wire length as a circuit complexity measure	8	2005
230	On the relevance of the shape of postsynaptic potentials for the computational power of Spiking Neurons	7	1995
231	Analysis of the computational strategy of a detailed laminar cortical microcircuit model for solving the image-change-detection task	6	2021
232	A precise characterization of the class of languages recognized by neural nets under gaussian and other common noise distributions	6	1998
233	Fast Approximation Algorithms for the Robot Placement Problem	6	1983
234	High α-recursively enumerable degrees	6	1978
235	Modeling circuit mechanisms of opposing cortical responses to visual flow perturbations	6	2024
236	Pulsed neural networks MIT Press	6	2021
237	The cortical microcircuitry of predictions and context: a multi-scale perspective	6	2024
238	The uniform regular set theorem in α-recursion theory1	6	1978
239	Competition between bottom-up visual input and internal inhibition generates error neurons in a model of the mouse primary visual cortex	5	2023
240	Integration of stimulus history in information conveyed by neurons in primary auditory cortex in response to tone sequences	5	2023