A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
SeReNe prunes neurons with low sensitivity to reduce network size.
Under-parameterized networks can either copy or average teacher weights, leading to universal optimal solutions.
Neuron Shapley identifies key neurons in deep networks, improving model accuracy and fairness.
Stable unactivated neurons reduce expressiveness in ReLU networks.
Neural networks learn to mimic brain neurons with two-input activation functions, improving performance and robustness.
Single-spike neurons can approximate as well as multi-spike neurons.
CHANI learns classification tasks with local transformations inspired by biology.
New training method for ReLU networks achieves optimal weight size for memorization.
"Sparse" neural networks, in which relatively few neurons or connections are active, are common in both machine learning and neuroscience. Whereas in machine learning, "sparsity" is related to a penalty term that leads to some connecting weights becoming small or zero, in biological brains, sparsity is often created wh…
The predictive power of neural networks often costs model interpretability. Several techniques have been developed for explaining model outputs in terms of input features; however, it is difficult to translate such interpretations into actionable insight. Here, we propose a framework to analyze predictions in terms of …
Single ReLU neuron's gradient dynamics reveal support vectors as key to generalization.
The interplay between inter-neuronal network topology and cognition has been studied deeply by connectomics researchers and network scientists, which is crucial towards understanding the remarkable efficacy of biological neural networks. Curiously, the deep learning revolution that revived neural networks has not paid …
Despite our extensive knowledge of biophysical properties of neurons, there is no commonly accepted algorithmic theory of neuronal function. Here we explore the hypothesis that single-layer neuronal networks perform online symmetric nonnegative matrix factorization (SNMF) of the similarity matrix of the streamed data. …
We view a neural network as a distributed system of which neurons can fail independently, and we evaluate its robustness in the absence of any (recovery) learning phase. We give tight bounds on the number of neurons that can fail without harming the result of a computation. To determine our bounds, we leverage the fact…
Optimal neuron activation functions improve neural network performance.
Recently, deep learning has achieved huge successes in many important applications. In our previous studies, we proposed quadratic/second-order neurons and deep quadratic neural networks. In a quadratic neuron, the inner product of a vector of data and the corresponding weights in a conventional neuron is replaced with…
The artificial neural network is a popular framework in machine learning. To empower individual neurons, we recently suggested that the current type of neurons could be upgraded to 2nd order counterparts, in which the linear operation between inputs to a neuron and the associated weights is replaced with a nonlinear qu…
This work makes vision networks more interpretable by identifying key neurons.
This paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The model provides adaptive and differentiable local connectivity (plasticity) applicable to any domain. It requires no other tool than the backpropagation algorithm to learn its parameters whi…
Improved NiNo networks accelerate Adam training by up to 50%.
Recent advances in neuroscience have revealed many principles about neural processing. In particular, many biological systems were found to reconfigure/recruit single neurons to generate multiple kinds of decisions. Such findings have the potential to advance our understanding of the design and optimization process of …
Single neuron with ADA learns XOR and outperforms other functions.
Neuron-specific dropout reduces overfitting and data needs for neural networks.
Novel method decorrelates neurons for better deep learning model generalization.
Local convergence theory for mildly over-parameterized neural nets.
Modeling hidden neurons in SNNs using mesoscopic approximations.
In this paper, some patterns of the Neuron Response of deep Convolutional Neural Networks were observed.
Inspired by complexity and diversity of biological neurons, our group proposed quadratic neurons by replacing the inner product in current artificial neurons with a quadratic operation on input data, thereby enhancing the capability of an individual neuron. Along this direction, we are motivated to evaluate the power o…
Novel 'strong neuron' improves deep learning efficiency and robustness.
Automated method finds meaningful directions in neural network activations.
Deep neural networks (DNNs) are known for extracting useful information from large amounts of data. However, the representations learned in DNNs are typically hard to interpret, especially in dense layers. One crucial issue of the classical DNN model such as multilayer perceptron (MLP) is that neurons in the same layer…
We propose the BinaryGAN, a novel generative adversarial network (GAN) that uses binary neurons at the output layer of the generator. We employ the sigmoid-adjusted straight-through estimators to estimate the gradients for the binary neurons and train the whole network by end-to-end backpropogation. The proposed model …
Mixed integer programming identifies critical neurons in neural networks.
Unseen or out-of-domain data can seriously degrade the performance of a neural network model, indicating the model's failure to generalize to unseen data. Neural net pruning can not only help to reduce a model's size but can improve the model's generalization capacity as well. Pruning approaches look for low-salient ne…
We propose a new generic type of stochastic neurons, called -neurons, that considers activation functions based on Jackson's -derivatives with stochastic parameters . Our generalization of neural network architectures with -neurons is shown to be both scalable and very easy to implement. We demonstrate expe…
Simplified neural network EFTs reveal a single critical condition.
Persistent neurons improve neural network optimization by leveraging previous solutions.
A new algorithm trains deep neural networks by adding neurons greedily.
Deep learning has recently led to great successes in tasks such as image recognition (e.g Krizhevsky et al., 2012). However, deep networks are still outmatched by the power and versatility of the brain, perhaps in part due to the richer neuronal computations available to cortical circuits. The challenge is to identify …
Gradient descent dynamics in neural networks show quenching and activation phases.
Neurons and networks in the cerebral cortex must operate reliably despite multiple sources of noise. To evaluate the impact of both input and output noise, we determine the robustness of single-neuron stimulus selective responses, as well as the robustness of attractor states of networks of neurons performing memory ta…
An artificial neuron is modelled as a weighted summation followed by an activation function which determines its output. A wide variety of activation functions such as rectified linear units (ReLU), leaky-ReLU, Swish, MISH, etc. have been explored in the literature. In this short paper, we explore what happens when the…
The challenge of assigning importance to individual neurons in a network is of interest when interpreting deep learning models. In recent work, Dhamdhere et al. proposed Total Conductance, a "natural refinement of Integrated Gradients" for attributing importance to internal neurons. Unfortunately, the authors found tha…
Study enhances neural network interpretability through statistical methods.
New metric captures individual neuron tuning across neural networks.
Unified approach for neural networks with multi-compartmental neurons and non-Hebbian plasticity.
Partial fusion combines neural networks to balance accuracy and efficiency.
Most deep neural networks use simple, fixed activation functions, such as sigmoids or rectified linear units, regardless of domain or network structure. We introduce differential equation units (DEUs), an improvement to modern neural networks, which enables each neuron to learn a particular nonlinear activation functio…