相关论文: Input Statistics and Hebbian Crosstalk Effects

In studies of the visual system as well as in computer vision, the focus is often on contrast edges. However, the primate visual system contains a large number of cells that are insensitive to spatial contrast and, instead, respond to…

The output signal is examined for the Jacobi neuronal model which is characterized by input-dependent multiplicative noise. The dependence of the noise on the rate of inhibition turns out to be of primary importance to observe maxima both…

Hausa texts are often characterized by writing anomalies, such as incorrect character substitutions and spacing errors, which sometimes hinder natural language processing (NLP) applications. This paper presents an approach to automatically…

The brain performs unsupervised learning and (perhaps) simultaneous supervised learning. This raises the question as to whether a hybrid of supervised and unsupervised methods will produce better learning. Inspired by the rich space of…

Modern deep learning science often assumes that neural networks learn from a fixed data distribution. However, many practically important learning problems involve data distributions that change throughout training. How does such…

Automatic Arabic diacritization is useful in many applications, ranging from reading support for language learners to accurate pronunciation predictor for downstream tasks like speech synthesis. While most of the previous works focused on…

The success of deep neural networks largely depends on the statistical structure of the training data. While learning dynamics and generalization on isotropic data are well-established, the impact of pronounced anisotropy on these crucial…

Lifelong learning and adaptability are two defining aspects of biological agents. Modern reinforcement learning (RL) approaches have shown significant progress in solving complex tasks, however once training is concluded, the found…

Local learning rules in biological neural networks (BNNs) are commonly referred to as Hebbian learning. [26] links a biologically motivated Hebbian learning rule to a specific zeroth-order optimization method. In this work, we study a…

The state space of a conventional Hopfield network typically exhibits many different attractors of which only a small subset satisfy constraints between neurons in a globally optimal fashion. It has recently been demonstrated that combining…

Learning and the ability to learn are important factors in development and evolutionary processes [1]. Depending on the level, the complexity of learning can strongly vary. While associative learning can explain simple learning behaviour…

Learning-to-Rank (LTR) models trained from implicit feedback (e.g. clicks) suffer from inherent biases. A well-known one is the position bias -- documents in top positions are more likely to receive clicks due in part to their position…

Shortcut learning, or `Clever Hans effect` refers to situations where a learning agent (e.g., deep neural networks) learns spurious correlations present in data, resulting in biased models. We focus on finding shortcuts in deep learning…

We apply a general theory describing the dynamics of supervised learning in layered neural networks in the regime where the size p of the training set is proportional to the number of inputs N, as developed in a previous paper, to several…

Although a plethora of architectural variants for deep classification has been introduced over time, recent works have found empirical evidence towards similarities in their training process. It has been hypothesized that neural networks…

Neural network training is typically viewed as gradient descent on a loss surface. We propose a fundamentally different perspective: learning is a structure-preserving transformation (a functor L) between the space of network parameters…

Recent works have demonstrated that the sample complexity of gradient-based learning of single index models, i.e. functions that depend on a 1-dimensional projection of the input data, is governed by their information exponent. However,…

Recent development in data-driven decision science has seen great advances in individualized decision making. Given data with individual covariates, treatment assignments and outcomes, researchers can search for the optimal individualized…

Learning models have been shown to rely on spurious correlations between non-predictive features and the associated labels in the training data, with negative implications on robustness, bias and fairness. In this work, we provide a…

Influence functions are a popular tool for attributing a model's output to training data. The traditional approach relies on the calculation of inverse Hessian-vector products (iHVP), but the classical solver "Linear time Stochastic…