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.
New learning algorithm mimics biological neural networks.
New learning rules for wide neural networks without backpropagation.
Biological neural network mimics CCA for multi-channel data.
Fault-tolerant neural networks inspired by biological error correction codes.
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 …
Oja's rule improves neural network training without engineered tricks.
Derives a biologically plausible neural network for Slow Feature Analysis.
In this work, we perform an exploratory study on synthesizing deep neural networks using biological synaptic strength distributions, and the potential influence of different distributions on modelling performance particularly for the scenario associated with small data sets. Surprisingly, a CNN with convolutional layer…
DeepSIBA predicts biological effects of chemical structures using graph neural networks.
Stochastic RNNs classify biological neural network paths with robust error bounds.
Deep neural networks (DNNs) transform stimuli across multiple processing stages to produce representations that can be used to solve complex tasks, such as object recognition in images. However, a full understanding of how they achieve this remains elusive. The complexity of biological neural networks substantially exc…
We introduce bio-inspired artificial neural networks consisting of neurons that are additionally characterized by spatial positions. To simulate properties of biological systems we add the costs penalizing long connections and the proximity of neurons in a two-dimensional space. Our experiments show that in the case wh…
Sparse neural networks visualize paired transcriptomic and electrophysiological data.
GAIT-prop derives a biologically plausible learning rule from backpropagation.
Graph auto-encoder predicts unobserved node features from biological networks and omics data.
This paper explores adaptive neural activation in RNNs for better learning.
New algorithm shows neural networks can learn without full backpropagation.
The power law has been observed in the degree distributions of many biological neural networks. Sparse deep neural networks, which learn an economical representation from the data, resemble biological neural networks in many ways. In this paper, we study if these artificial networks also exhibit properties of the power…
Proposes a new neural network approach to credit assignment.
New algorithm for online training of Spiking Neural Networks (SNNs).
Deep learning applied to biological data mining.
In real world scenarios, objects are often partially occluded. This requires a robustness for object recognition against these perturbations. Convolutional networks have shown good performances in classification tasks. The learned convolutional filters seem similar to receptive fields of simple cells found in the prima…
Abstract: Investigates the role of activation functions in neural networks and their physical basis.
Neural network models of early sensory processing typically reduce the dimensionality of streaming input data. Such networks learn the principal subspace, in the sense of principal component analysis (PCA), by adjusting synaptic weights according to activity-dependent learning rules. When derived from a principled cost…
DASH simplifies neural networks for gene regulatory dynamics using domain knowledge.
Defines metrics to compare neural network representations.
engGNN combines external and generated graphs to improve disease classification and biomarker discovery.
New learning rules from information bottleneck improve deep learning without precise labels.
Log-Normal Multiplicative Dynamics improves low-precision training of neural networks.
Deep neural networks correct Mie scattering in FTIR spectra of biological samples.
Substring kernels are classical tools for representing biological sequences or text. However, when large amounts of annotated data are available, models that allow end-to-end training such as neural networks are often preferred. Links between recurrent neural networks (RNNs) and substring kernels have recently been dra…
Two local learning rules are investigated to avoid weight transport in neural networks.
New mechanisms from primate vision improve neural network robustness.
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…
This paper presents a constructive algorithm that achieves successful one-shot learning of hidden spike-patterns in a competitive detection task. It has previously been shown (Masquelier et al., 2008) that spike-timing-dependent plasticity (STDP) and lateral inhibition can result in neurons competitively tuned to repea…
While deep learning has led to remarkable advances across diverse applications, it struggles in domains where the data distribution changes over the course of learning. In stark contrast, biological neural networks continually adapt to changing domains, possibly by leveraging complex molecular machinery to solve many t…
This project proposes using reinforcement learning to train spiking neural networks.
A new model for sequential memory using temporal predictive coding.
AR algorithm simplifies backpropagation with improved scalability and biological plausibility.
The Backpropagation algorithm relies on the abstraction of using a neural model that gets rid of the notion of time, since the input is mapped instantaneously to the output. In this paper, we claim that this abstraction of ignoring time, along with the abrupt input changes that occur when feeding the training set, are …
While neural networks are powerful approximators used to classify or embed data into lower dimensional spaces, they are often regarded as black boxes with uninterpretable features. Here we propose Graph Spectral Regularization for making hidden layers more interpretable without significantly impacting performance on th…
Study adapts AI research methods to analyze image augmentation impacts on neural network operations.
Training deep neural networks with the error backpropagation algorithm is considered implausible from a biological perspective. Numerous recent publications suggest elaborate models for biologically plausible variants of deep learning, typically defining success as reaching around 98% test accuracy on the MNIST data se…
The quest for biologically plausible deep learning is driven, not just by the desire to explain experimentally-observed properties of biological neural networks, but also by the hope of discovering more efficient methods for training artificial networks. In this paper, we propose a new algorithm named Variational Proba…
Gated recurrent units (GRUs) are specialized memory elements for building recurrent neural networks. Despite their incredible success on various tasks, including extracting dynamics underlying neural data, little is understood about the specific dynamics representable in a GRU network. As a result, it is both difficult…
Paper semantifies bioassay text using neural networks.
One conjecture in both deep learning and classical connectionist viewpoint is that the biological brain implements certain kinds of deep networks as its back-end. However, to our knowledge, a detailed correspondence has not yet been set up, which is important if we want to bridge between neuroscience and machine learni…
Neural networks have shown great potential in many applications like speech recognition, drug discovery, image classification, and object detection. Neural network models are inspired by biological neural networks, but they are optimized to perform machine learning tasks on digital computers. The proposed work explores…