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.
Spatially positioned neurons in neural networks mimic biological systems.
DCNs mimic neuronal networks for improved neural classification.
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…
New learning algorithm mimics biological neural networks.
Biological neurons learn tensor decompositions of higher-order correlations using nonlinear Hebbian plasticity.
Biological neural network mimics CCA for multi-channel data.
Fault-tolerant neural networks inspired by biological error correction codes.
Proposes a new neural network architecture inspired by biology to improve learning and information flow.
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. …
A new theory explains large associative memory with biological plausibility.
The practical success of widely used machine learning (ML) and deep learning (DL) algorithms in Artificial Intelligence (AI) community owes to availability of large datasets for training and huge computational resources. Despite the enormous practical success of AI, these algorithms are only loosely inspired from the b…
A new neural model evolves to learn at the synaptic level.
RNNs are suboptimal at compressing past sensory inputs for future prediction.
Neurons predict future scalar inputs by learning top modes of lag vectors.
Despite its size and complexity, the human cortex exhibits striking anatomical regularities, suggesting there may simple meta-algorithms underlying cortical learning and computation. We expect such meta-algorithms to be of interest since they need to operate quickly, scalably and effectively with little-to-no specializ…
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…
A new SNN model explains decision-making with learning and spiking neurons.
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…
Deep learning is a subset of a broader family of machine learning methods based on learning data representations. These models are inspired by human biological nervous systems, even if there are various differences pertaining to the structural and functional properties of biological brains. The elementary constituents …
A new learning framework mimics biological STDP for neural networks.
This paper explores adaptive neural activation in RNNs for better learning.
`Biologically inspired' activation functions, such as the logistic sigmoid, have been instrumental in the historical advancement of machine learning. However in the field of deep learning, they have been largely displaced by rectified linear units (ReLU) or similar functions, such as its exponential linear unit (ELU) v…
We propose a neural information processing system which is obtained by re-purposing the function of a biological neural circuit model, to govern simulated and real-world control tasks. Inspired by the structure of the nervous system of the soil-worm, C. elegans, we introduce Neuronal Circuit Policies (NCPs), defined as…
Automated method finds meaningful directions in neural network activations.
Understanding the morphological changes of primary neuronal cells induced by chemical compounds is essential for drug discovery. Using the data from a single high-throughput imaging assay, a classification model for predicting the biological activity of candidate compounds was introduced. The image recognition model wh…
Improved Bayesian inference for neuronal ensemble inference reduces computational cost.
Backpropagation is explained as a diffusion process in neural networks.
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…
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…
Modeling hidden neurons in SNNs using mesoscopic approximations.
New algorithm shows neural networks can learn without full backpropagation.
BDH model learns like the brain, rivaling Transformer performance.
New estimator corrects bias in CKA for sparsely sampled neurons.
Neural networks learn to mimic brain neurons with two-input activation functions, improving performance and robustness.
CHANI learns classification tasks with local transformations inspired by biology.
Error backpropagation is a highly effective mechanism for learning high-quality hierarchical features in deep networks. Updating the features or weights in one layer, however, requires waiting for the propagation of error signals from higher layers. Learning using delayed and non-local errors makes it hard to reconcile…
This brief note highlights some basic concepts required toward understanding the evolution of machine learning and deep learning models. The note starts with an overview of artificial intelligence and its relationship to biological neuron that ultimately led to the evolution of todays intelligent models.
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…
A new model uses 'ghost units' to enable efficient backpropagation in deep neural networks.
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 …
Researchers develop methods to learn neuron dynamics from colored noise.
Abstract: Investigates the role of activation functions in neural networks and their physical basis.
Natural gradient learning improves synaptic plasticity in spiking neurons.
SpaRCe optimizes reservoir computing by learning neuron thresholds to improve performance and prevent forgetting.
AR algorithm simplifies backpropagation with improved scalability and biological plausibility.
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 …
New method decomposes sensory information from neurons into specific stimuli and features.
By and large, Backpropagation (BP) is regarded as one of the most important neural computation algorithms at the basis of the progress in machine learning, including the recent advances in deep learning. However, its computational structure has been the source of many debates on its arguable biological plausibility. In…