paper-with-me

Papers

Sign Gradient Descent-based Neuronal Dynamics: ANN-to-SNN Conversion Beyond ReLU Network

2024-07-01 · Hyunseok Oh, Youngki Lee

Spiking neural network (SNN) is studied in multidisciplinary domains to (i) enable order-of-magnitudes energy-efficient AI inference and (ii) computationally simulate neuro-scientific mechanisms. The lack of discrete theory obstructs the practical application of SNN by limiting its performance and nonlinearity support. We present a new optimization-theoretic perspective of the discrete dynamics of spiking neurons. We prove that a discrete dynamical system of simple integrate-and-fire models approximates the sub-gradient method over unconstrained optimization problems. We practically extend our theory to introduce a novel sign gradient descent (signGD)-based neuronal dynamics that can (i) approximate diverse nonlinearities beyond ReLU and (ii) advance ANN-to-SNN conversion performance in low time steps. Experiments on large-scale datasets show that our technique achieves (i) state-of-the-art performance in ANN-to-SNN conversion and (ii) is the first to convert new DNN architectures, e.g., ConvNext, MLP-Mixer, and ResMLP. We publicly share our source code at https://github.com/snuhcs/snn_signgd .

📄 PDF Abstract BibTeX arXiv:2407.01645

Code (1)

snuhcs/snn_signgd 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Average Pooling 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Affine Operator 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Neural dynamics under active inference: plausibility and efficiency of information processing

2020-01-22 · Lancelot Da Costa, Thomas Parr, Biswa Sengupta, Karl Friston

Active inference is a normative framework for explaining behaviour under the free energy principle -- a theory of self-organisation originating in neuroscience. It specifies neuronal dynamics for state-estimation in term…

State Estimation

Backpropagation through space, time, and the brain

2024-03-25 · Benjamin Ellenberger, Paul Haider, Jakob Jordan, Kevin Max 외

How physical networks of neurons, bound by spatio-temporal locality constraints, can perform efficient credit assignment, remains, to a large extent, an open question. In machine learning, the answer is almost universall…

Faster Biological Gradient Descent Learning

2020-09-27 · Ho Ling Li

Back-propagation is a popular machine learning algorithm that uses gradient descent in training neural networks for supervised learning, but can be very slow. A number of algorithms have been developed to speed up conver…

Spike-timing-dependent Hebbian learning as noisy gradient descent

2025-05-15 · Niklas Dexheimer, Sascha Gaudlitz, Johannes Schmidt-Hieber

Hebbian learning is a key principle underlying learning in biological neural networks. It postulates that synaptic changes occur locally, depending on the activities of pre- and postsynaptic neurons. While Hebbian learni…

Proximal Mean Field Learning in Shallow Neural Networks

2022-10-25 · Alexis Teter, Iman Nodozi, Abhishek Halder

We propose a custom learning algorithm for shallow over-parameterized neural networks, i.e., networks with single hidden layer having infinite width. The infinite width of the hidden layer serves as an abstraction for th…

Multi-class Classification