English
Related papers

Related papers: The staircase property: How hierarchical structure…

200 papers

Deep learning has been widely used for supervised learning and classification/regression problems. Recently, a novel area of research has applied this paradigm to unsupervised tasks; indeed, a gradient-based approach extracts, efficiently…

Machine Learning · Statistics 2020-09-08 Giansalvo Cirrincione , Pietro Barbiero , Gabriele Ciravegna , Vincenzo Randazzo

Hierarchical neural networks are exponentially more efficient than their corresponding "shallow" counterpart with the same expressive power, but involve huge number of parameters and require tedious amounts of training. By approximating the…

Machine Learning · Computer Science 2019-12-20 Bálint Daróczy , Rita Aleksziev , András Benczúr

We introduce a flexible setup allowing for a neural network to learn both its size and topology during the course of a standard gradient-based training. The resulting network has the structure of a graph tailored to the particular learning…

Machine Learning · Computer Science 2020-07-16 Romuald A. Janik , Aleksandra Nowak

Neural networks trained with gradient-based methods exhibit a strong simplicity bias: they learn simpler statistical features of their data before moving to more complex features. Previous analyses of this phenomenon have largely focused on…

Machine Learning · Statistics 2026-05-19 Fabiola Ricci , Claudia Merger , Sebastian Goldt

Recurrent neural network is a powerful model that learns temporal patterns in sequential data. For a long time, it was believed that recurrent networks are difficult to train using simple optimizers, such as stochastic gradient descent, due…

Neural and Evolutionary Computing · Computer Science 2015-04-20 Tomas Mikolov , Armand Joulin , Sumit Chopra , Michael Mathieu , Marc'Aurelio Ranzato

Low precision weights, activations, and gradients have been proposed as a way to improve the computational efficiency and memory footprint of deep neural networks. Recently, low precision networks have even shown to be more robust to…

Machine Learning · Computer Science 2018-07-04 Griffin Lacey , Graham W. Taylor , Shawki Areibi

Feature extraction - the ability to identify relevant properties of data - is a key factor underlying the success of deep learning. Yet, it has proved difficult to elucidate its nature within existing predictive theories, to the extent that…

Disordered Systems and Neural Networks · Physics 2025-08-29 Andrea Corti , Rosalba Pacelli , Pietro Rotondo , Marco Gherardi

In this paper, we propose a new first-order gradient-based algorithm to train deep neural networks. We first introduce the sign operation of stochastic gradients (as in sign-based methods, e.g., SIGN-SGD) into ADAM, which is called as…

Computer Vision and Pattern Recognition · Computer Science 2019-07-23 Dong Wang , Yicheng Liu , Wenwo Tang , Fanhua Shang , Hongying Liu , Qigong Sun , Licheng Jiao

Numerous social, medical, engineering and biological challenges can be framed as graph-based learning tasks. Here, we propose a new feature based approach to network classification. We show how dynamics on a network can be useful to reveal…

Machine Learning · Statistics 2017-06-01 Leonardo Gutierrez Gomez , Benjamin Chiem , Jean-Charles Delvenne

We report a series of robust empirical observations, demonstrating that deep Neural Networks learn the examples in both the training and test sets in a similar order. This phenomenon is observed in all the commonly used benchmarks we…

Machine Learning · Computer Science 2023-12-29 Guy Hacohen , Leshem Choshen , Daphna Weinshall

This paper investigates the foundations of deep learning through insight of geometry, algebra and differential calculus. At is core, artificial intelligence relies on assumption that data and its intrinsic structure can be embedded into…

Differential Geometry · Mathematics 2025-10-22 Tsemo Aristide

The current deep learning model is of a single-grade, that is, it learns a deep neural network by solving a single nonconvex optimization problem. When the layer number of the neural network is large, it is computationally challenging to…

Machine Learning · Computer Science 2023-02-02 Yuesheng Xu

Hierarchical learning algorithms that gradually approximate a solution to a data-driven optimization problem are essential to decision-making systems, especially under limitations on time and computational resources. In this study, we…

Machine Learning · Computer Science 2023-03-22 Christos Mavridis , John Baras

We study the problem of learning a Bayesian network (BN) of a set of variables when structural side information about the system is available. It is well known that learning the structure of a general BN is both computationally and…

Machine Learning · Computer Science 2021-12-22 Ehsan Mokhtarian , Sina Akbari , Fateme Jamshidi , Jalal Etesami , Negar Kiyavash

Deep learning has led to significant advances in artificial intelligence, in part, by adopting strategies motivated by neurophysiology. However, it is unclear whether deep learning could occur in the real brain. Here, we show that a deep…

Neurons and Cognition · Quantitative Biology 2017-04-11 Jordan Guergiuev , Timothy P. Lillicrap , Blake A. Richards

In this paper, we focus on the unsupervised setting for structure learning of deep neural networks and propose to adopt the efficient coding principle, rooted in information theory and developed in computational neuroscience, to guide the…

Machine Learning · Computer Science 2021-05-31 Jinhui Yuan , Fei Pan , Chunting Zhou , Tao Qin , Tie-Yan Liu

Deep unrolling, or unfolding, is an emerging learning-to-optimize method that unrolls a truncated iterative algorithm in the layers of a trainable neural network. However, the convergence guarantees and generalizability of the unrolled…

Machine Learning · Computer Science 2024-12-02 Samar Hadou , Navid NaderiAlizadeh , Alejandro Ribeiro

Computational learning theory states that many classes of boolean formulas are learnable in polynomial time. This paper addresses the understudied subject of how, in practice, such formulas can be learned by deep neural networks.…

Machine Learning · Computer Science 2025-09-17 Marcio Nicolau , Anderson R. Tavares , Zhiwei Zhang , Pedro Avelar , João M. Flach , Luis C. Lamb , Moshe Y. Vardi

A long-standing goal in deep learning has been to characterize the learning behavior of black-box models in a more interpretable manner. For graph neural networks (GNNs), considerable advances have been made in formalizing what functions…

Machine Learning · Computer Science 2024-06-19 Chenxiao Yang , Qitian Wu , David Wipf , Ruoyu Sun , Junchi Yan

The ability to design complex neural network architectures which enable effective training by stochastic gradient descent has been the key for many achievements in the field of deep learning. However, developing such architectures remains a…

Neural and Evolutionary Computing · Computer Science 2019-07-04 Marcus Märtens , Dario Izzo