Cengiz Pehlevan

Orcid: 0000-0001-9767-6063

According to our database1, Cengiz Pehlevan authored at least 66 papers between 2013 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
A Dynamical Model of Neural Scaling Laws.
CoRR, 2024

2023
Grokking as the Transition from Lazy to Rich Training Dynamics.
CoRR, 2023

Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit.
CoRR, 2023

Dynamics of Temporal Difference Reinforcement Learning.
CoRR, 2023

Learning Curves for Heterogeneous Feature-Subsampled Ridge Ensembles.
CoRR, 2023

Neural networks learn to magnify areas near decision boundaries.
CoRR, 2023

Learning Curves for Deep Structured Gaussian Feature Models.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Neural Circuits for Fast Poisson Compressed Sensing in the Olfactory Bulb.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Learning Curves for Noisy Heterogeneous Feature-Subsampled Ridge Ensembles.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Long Sequence Hopfield Memory.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Correlative Information Maximization: A Biologically Plausible Approach to Supervised Deep Neural Networks without Weight Symmetry.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Loss Dynamics of Temporal Difference Reinforcement Learning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Feature-Learning Networks Are Consistent Across Widths At Realistic Scales.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Interneurons accelerate learning dynamics in recurrent neural networks for statistical adaptation.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Correlative Information Maximization Based Biologically Plausible Neural Networks for Correlated Source Separation.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022
On Neural Network Kernels and the Storage Capacity Problem.
Neural Comput., 2022

Bandwidth Enables Generalization in Quantum Kernel Models.
CoRR, 2022

Contrasting random and learned features in deep Bayesian linear regression.
CoRR, 2022

Biologically plausible single-layer networks for nonnegative independent component analysis.
Biol. Cybern., 2022

Natural gradient enables fast sampling in spiking neural networks.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Biologically-Plausible Determinant Maximization Neural Networks for Blind Separation of Correlated Sources.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?
Proceedings of the Tenth International Conference on Learning Representations, 2022

Learning Curves for SGD on Structured Features.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Neural Networks as Kernel Learners: The Silent Alignment Effect.
Proceedings of the Tenth International Conference on Learning Representations, 2022

A Kernel Analysis of Feature Learning in Deep Neural Networks.
Proceedings of the 58th Annual Allerton Conference on Communication, 2022

2021
Contrastive Similarity Matching for Supervised Learning.
Neural Comput., 2021

Asymptotics of representation learning in finite Bayesian neural networks.
CoRR, 2021

Exact priors of finite neural networks.
CoRR, 2021

Exact marginal prior distributions of finite Bayesian neural networks.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Asymptotics of representation learning in finite Bayesian neural networks.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Out-of-Distribution Generalization in Kernel Regression.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Attention Approximates Sparse Distributed Memory.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Depth induces scale-averaging in overparameterized linear Bayesian neural networks.
Proceedings of the 55th Asilomar Conference on Signals, Systems, and Computers, 2021

2020
Neurons as Canonical Correlation Analyzers.
Frontiers Comput. Neurosci., 2020

Activation function dependence of the storage capacity of treelike neural networks.
CoRR, 2020

Statistical Mechanics of Generalization in Kernel Regression.
CoRR, 2020

Supervised Deep Similarity Matching.
CoRR, 2020

Minimax Dynamics of Optimally Balanced Spiking Networks of Excitatory and Inhibitory Neurons.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Associative Memory in Iterated Overparameterized Sigmoid Autoencoders.
Proceedings of the 37th International Conference on Machine Learning, 2020

Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks.
Proceedings of the 37th International Conference on Machine Learning, 2020

Blind Bounded Source Separation Using Neural Networks with Local Learning Rules.
Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2019
Neuroscience-Inspired Online Unsupervised Learning Algorithms: Artificial neural networks.
IEEE Signal Process. Mag., 2019

Neuroscience-inspired online unsupervised learning algorithms.
CoRR, 2019

Structured and Deep Similarity Matching via Structured and Deep Hebbian Networks.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

A Spiking Neural Network with Local Learning Rules Derived from Nonnegative Similarity Matching.
Proceedings of the IEEE International Conference on Acoustics, 2019

A Closer Look at Disentangling in β-VAE.
Proceedings of the 53rd Asilomar Conference on Signals, Systems, and Computers, 2019

2018
Why Do Similarity Matching Objectives Lead to Hebbian/Anti-Hebbian Networks?
Neural Comput., 2018

Manifold-tiling Localized Receptive Fields are Optimal in Similarity-preserving Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Efficient Principal Subspace Projection of Streaming Data Through Fast Similarity Matching.
Proceedings of the IEEE International Conference on Big Data (IEEE BigData 2018), 2018

Biologically Plausible Online Principal Component Analysis Without Recurrent Neural Dynamics.
Proceedings of the 52nd Asilomar Conference on Signals, Systems, and Computers, 2018

2017
Blind Nonnegative Source Separation Using Biological Neural Networks.
Neural Comput., 2017

Adversarial synapses: Hebbian/anti-Hebbian learning optimizes min-max objectives.
CoRR, 2017

Resource-efficient perceptron has sparse synaptic weight distribution.
Proceedings of the 25th Signal Processing and Communications Applications Conference, 2017

A clustering neural network model of insect olfaction.
Proceedings of the 51st Asilomar Conference on Signals, Systems, and Computers, 2017

2016
Self-calibrating neural networks for dimensionality reduction.
Proceedings of the 50th Asilomar Conference on Signals, Systems and Computers, 2016

Do retinal ganglion cells project natural scenes to their principal subspace and whiten them?
Proceedings of the 50th Asilomar Conference on Signals, Systems and Computers, 2016

2015
A Hebbian/Anti-Hebbian Neural Network for Linear Subspace Learning: A Derivation from Multidimensional Scaling of Streaming Data.
Neural Comput., 2015

A Normative Theory of Adaptive Dimensionality Reduction in Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, 2015

Optimization theory of Hebbian/anti-Hebbian networks for PCA and whitening.
Proceedings of the 53rd Annual Allerton Conference on Communication, 2015

2014
A Hebbian/Anti-Hebbian network derived from online non-negative matrix factorization can cluster and discover sparse features.
Proceedings of the 48th Asilomar Conference on Signals, Systems and Computers, 2014

A Hebbian/Anti-Hebbian network for online sparse dictionary learning derived from symmetric matrix factorization.
Proceedings of the 48th Asilomar Conference on Signals, Systems and Computers, 2014

2013
A neuron as a signal processing device.
Proceedings of the 2013 Asilomar Conference on Signals, 2013


  Loading...