English
Related papers

Related papers: Feed-Forward Neural Networks Need Inductive Bias t…

200 papers

A efficient incremental learning algorithm for classification tasks, called NetLines, well adapted for both binary and real-valued input patterns is presented. It generates small compact feedforward neural networks with one hidden layer of…

Artificial Intelligence · Computer Science 2009-04-30 Juan-Manuel Torres-Moreno , Mirta B. Gordon

Training of deep models for classification tasks is hindered by local minima problems and vanishing gradients, while unsupervised layer-wise pretraining does not exploit information from class labels. Here, we propose a new regularization…

Machine Learning · Computer Science 2019-11-07 Pavel Sulimov , Elena Sukmanova , Roman Chereshnev , Attila Kertesz-Farkas

Convolutional neural networks have achieved astonishing results in different application areas. Various methods that allow us to use these models on mobile and embedded devices have been proposed. Especially binary neural networks are a…

Machine Learning · Computer Science 2018-12-06 Joseph Bethge , Marvin Bornstein , Adrian Loy , Haojin Yang , Christoph Meinel

Although deep neural networks can achieve human-level performance on many object recognition benchmarks, prior work suggests that these same models fail to learn simple abstract relations, such as determining whether two objects are the…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Alexa R. Tartaglini , Sheridan Feucht , Michael A. Lepori , Wai Keen Vong , Charles Lovering , Brenden M. Lake , Ellie Pavlick

There is a concerted effort to build domain-general artificial intelligence in the form of universal neural network models with sufficient computational flexibility to solve a wide variety of cognitive tasks but without requiring…

Neural and Evolutionary Computing · Computer Science 2023-03-27 Jascha Achterberg , Danyal Akarca , Moataz Assem , Moritz Heimbach , Duncan E. Astle , John Duncan

Endowing robots with human-like physical reasoning abilities remains challenging. We argue that existing methods often disregard spatio-temporal relations and by using Graph Neural Networks (GNNs) that incorporate a relational inductive…

Machine Learning · Computer Science 2019-10-24 Fabio Ferreira , Lin Shao , Tamim Asfour , Jeannette Bohg

Contemporary wisdom based on empirical studies suggests that standard recurrent neural networks (RNNs) do not perform well on tasks requiring long-term memory. However, precise reasoning for this behavior is still unknown. This paper…

Machine Learning · Computer Science 2021-01-21 Melikasadat Emami , Mojtaba Sahraee-Ardakan , Parthe Pandit , Sundeep Rangan , Alyson K. Fletcher

Background. A main theoretical puzzle is why over-parameterized Neural Networks (NNs) generalize well when trained to zero loss (i.e., so they interpolate the data). Usually, the NN is trained with Stochastic Gradient Descent (SGD) or one…

Machine Learning · Computer Science 2025-02-18 Gon Buzaglo , Itamar Harel , Mor Shpigel Nacson , Alon Brutzkus , Nathan Srebro , Daniel Soudry

There is a significant performance gap between Binary Neural Networks (BNNs) and floating point Deep Neural Networks (DNNs). We propose to improve the binary training method, by introducing a new regularization function that encourages…

Machine Learning · Computer Science 2020-04-22 Sajad Darabi , Mouloud Belbahri , Matthieu Courbariaux , Vahid Partovi Nia

Modeling uncertainty in deep neural networks, despite recent important advances, is still an open problem. Bayesian neural networks are a powerful solution, where the prior over network weights is a design choice, often a normal…

Machine Learning · Statistics 2019-10-29 Raanan Y. Rohekar , Yaniv Gurwicz , Shami Nisimov , Gal Novik

In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch. When using fine-tuning, the underlying assumption is that the pre-trained model extracts generic features, which…

Machine Learning · Computer Science 2018-06-07 Xuhong Li , Yves Grandvalet , Franck Davoine

In this paper, we show that standard feed-forward and recurrent neural networks fail to learn abstract patterns based on identity rules. We propose Relation Based Pattern (RBP) extensions to neural network structures that solve this problem…

Machine Learning · Computer Science 2020-07-07 Tillman Weyde , Radha Manisha Kopparti

The notion of equality (identity) is simple and ubiquitous, making it a key case study for broader questions about the representations supporting abstract relational reasoning. Previous work suggested that neural networks were not suitable…

Machine Learning · Computer Science 2022-05-03 Atticus Geiger , Alexandra Carstensen , Michael C. Frank , Christopher Potts

The learning dynamics of biological brains and artificial neural networks are of interest to both neuroscience and machine learning. A key difference between them is that neural networks are often trained from a randomly initialized state…

Neural and Evolutionary Computing · Computer Science 2025-05-19 Benjamin Midler , Alejandro Pan Vazquez

While a lot of progress has been made in recent years, the dynamics of learning in deep nonlinear neural networks remain to this day largely misunderstood. In this work, we study the case of binary classification and prove various…

Machine Learning · Computer Science 2020-12-15 Remi Tachet , Mohammad Pezeshki , Samira Shabanian , Aaron Courville , Yoshua Bengio

Neural networks often learn to make predictions that overly rely on spurious correlation existing in the dataset, which causes the model to be biased. While previous work tackles this issue by using explicit labeling on the spuriously…

Machine Learning · Computer Science 2020-11-24 Junhyun Nam , Hyuntak Cha , Sungsoo Ahn , Jaeho Lee , Jinwoo Shin

Deep neural networks such as BERT have made great progress in relation classification. Although they can achieve good performance, it is still a question of concern whether these models recognize the directionality of relations, especially…

Computation and Language · Computer Science 2021-12-02 Shengfei Lyu , Xingyu Wu , Jinlong Li , Qiuju Chen , Huanhuan Chen

Residual connections remain ubiquitous in modern neural network architectures nearly a decade after their introduction. Their widespread adoption is often credited to their dramatically improved trainability: residual networks train faster,…

Machine Learning · Computer Science 2025-06-18 Christian H. X. Ali Mehmeti-Göpel , Michael Wand

Training data is always finite, making it unclear how to generalise to unseen situations. But, animals do generalise, wielding Occam's razor to select a parsimonious explanation of their observations. How they do this is called their…

Neurons and Cognition · Quantitative Biology 2023-07-20 William Dorrell , Maria Yuffa , Peter Latham

Artificial neural networks can acquire many aspects of human knowledge from data, making them promising as models of human learning. But what those networks can learn depends upon their inductive biases -- the factors other than the data…

Machine Learning · Computer Science 2025-02-28 Gianluca Bencomo , Max Gupta , Ioana Marinescu , R. Thomas McCoy , Thomas L. Griffiths