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.
A new method improves fitting neural data with spiking network models.
This paper proposes an alternating back-propagation algorithm for learning the generator network model. The model is a non-linear generalization of factor analysis. In this model, the mapping from the continuous latent factors to the observed signal is parametrized by a convolutional neural network. The alternating bac…
A new gradient method reduces variance for non-reparameterizable distributions.
The back-propagation algorithm is the cornerstone of deep learning. Despite its importance, few variations of the algorithm have been attempted. This work presents an approach to discover new variations of the back-propagation equation. We use a domain specific lan- guage to describe update equations as a list of primi…
Truncated back-propagation improves hyperparameter tuning and meta learning efficiency.
A new method prunes activation gradients to speed up CNN training.
As traditional neural network consumes a significant amount of computing resources during back propagation, \citet{Sun2017mePropSB} propose a simple yet effective technique to alleviate this problem. In this technique, only a small subset of the full gradients are computed to update the model parameters. In this paper …
We show how well known rules of back propagation arise from a weighted combination of finite automata. By redefining a finite automata as a predictor we combine the set of all -state finite automata using a weighted majority algorithm. This aggregated prediction algorithm can be simplified using symmetry, and we pro…
The back-propagation algorithm is widely used for learning in artificial neural networks. A challenge in machine learning is to create models that generalize to new data samples not seen in the training data. Recently, a common flaw in several machine learning algorithms was discovered: small perturbations added to the…
Proposes a semi-implicit back propagation method for neural networks.
Deep networks trained with Hebbian updates perform similarly to back-propagation on image datasets.
Visualizes ConvNets without confounding effects.
Paper classifies heart sound recordings as normal or abnormal.
The paper introduces various gradient descent algorithms for training deep learning models.
The study learns neural update rules by remembering past experiences.
NoProp learns neural networks without full back-propagation or forward-propagation.
Artificial neural networks are most commonly trained with the back-propagation algorithm, where the gradient for learning is provided by back-propagating the error, layer by layer, from the output layer to the hidden layers. A recently discovered method called feedback-alignment shows that the weights used for propagat…
In this paper, we revisit the recurrent back-propagation (RBP) algorithm, discuss the conditions under which it applies as well as how to satisfy them in deep neural networks. We show that RBP can be unstable and propose two variants based on conjugate gradient on the normal equations (CG-RBP) and Neumann series (Neuma…
ChOracle predicts user return times to improve churn prediction.
Paper uses AI to predict stock market volatility with neural networks and genetic algorithms.
Defines a calculus for integrating Moreau envelopes in differentiable programming.
A new backprop method reduces memory usage for deep neural networks.
Paper learns dynamic generator models for video sequences.
We marry ideas from deep neural networks and approximate Bayesian inference to derive a generalised class of deep, directed generative models, endowed with a new algorithm for scalable inference and learning. Our algorithm introduces a recognition model to represent approximate posterior distributions, and that acts as…
New method adapts without backprop, faster and better.
Optimization-based pruning eliminates backpropagation for large language models.
We propose a simple yet effective technique to simplify the training and the resulting model of neural networks. In back propagation, only a small subset of the full gradient is computed to update the model parameters. The gradient vectors are sparsified in such a way that only the top-k elements (in terms of magnitude…
EXODUS improves training of SNNs by stabilizing gradients and reducing complexity.
We identify a strong equivalence between neural network based machine learning (ML) methods and the formulation of statistical data assimilation (DA), known to be a problem in statistical physics. DA, as used widely in physical and biological sciences, systematically transfers information in observations to a model of …
Finding biologically plausible alternatives to back-propagation of errors is a fundamentally important challenge in artificial neural network research. In this paper, we propose a learning algorithm called error-driven Local Representation Alignment (LRA-E), which has strong connections to predictive coding, a theory t…
Due to the extremely volatile nature of financial markets, it is commonly accepted that stock price prediction is a task full of challenge. However in order to make profits or understand the essence of equity market, numerous market participants or researchers try to forecast stock price using various statistical, econ…
ILM-Norm normalizes instances individually for better performance.
A new adversarial DBN framework for deep learning.
FrequentNet uses frequency domain basis vectors for image classification, making models more interpretable and efficient.
PLIs improve classifier performance by fine-tuning latent representations.
Recent changes to greenhouse gas emission policies are catalyzing the electric vehicle (EV) market making it readily accessible to consumers. While there are challenges that arise with dense deployment of EVs, one of the major future concerns is cyber security threat. In this paper, cyber security threats in the form o…
Stochastic gradient descent (SGD) has achieved great success in training deep neural network, where the gradient is computed through back-propagation. However, the back-propagated values of different layers vary dramatically. This inconsistence of gradient magnitude across different layers renders optimization of deep …
Deep switch networks generate discrete data and language.
Connections between nodes of fully connected neural networks are usually represented by weight matrices. In this article, functional transfer matrices are introduced as alternatives to the weight matrices: Instead of using real weights, a functional transfer matrix uses real functions with trainable parameters to repre…
Statistical relational AI (StarAI) aims at reasoning and learning in noisy domains described in terms of objects and relationships by combining probability with first-order logic. With huge advances in deep learning in the current years, combining deep networks with first-order logic has been the focus of several recen…
A new learning framework mimics biological STDP for neural networks.
Using back-propagation and its variants to train deep networks is often problematic for new users. Issues such as exploding gradients, vanishing gradients, and high sensitivity to weight initialization strategies often make networks difficult to train, especially when users are experimenting with new architectures. Her…
Formula for complex SVD backpropagation developed.
Tackling pattern recognition problems in areas such as computer vision, bioinformatics, speech or text recognition is often done best by taking into account task-specific statistical relations between output variables. In structured prediction, this internal structure is used to predict multiple outputs simultaneously,…
We show how a deep denoising autoencoder with lateral connections can be used as an auxiliary unsupervised learning task to support supervised learning. The proposed model is trained to minimize simultaneously the sum of supervised and unsupervised cost functions by back-propagation, avoiding the need for layer-wise pr…
In this study, we propose the integration of competitive learning into convolutional neural networks (CNNs) to improve the representation learning and efficiency of fine-tuning. Conventional CNNs use back propagation learning, and it enables powerful representation learning by a discrimination task. However, it require…
TrISec generates imperceptible attacks without needing training data.
Paper tackles incremental few-shot learning with novel classes.