English
Related papers

Related papers: On residual network depth

200 papers

In this paper, we propose a novel ensembling technique for deep neural networks, which is able to drastically reduce the required memory compared to alternative approaches. In particular, we propose to extract multiple sub-networks from a…

Machine Learning · Computer Science 2022-10-07 Jary Pomponi , Simone Scardapane , Aurelio Uncini

Expressive efficiency refers to the relation between two architectures A and B, whereby any function realized by B could be replicated by A, but there exists functions realized by A, which cannot be replicated by B unless its size grows…

Machine Learning · Computer Science 2018-02-27 Or Sharir , Amnon Shashua

The training of deep residual neural networks (ResNets) with backpropagation has a memory cost that increases linearly with respect to the depth of the network. A way to circumvent this issue is to use reversible architectures. In this…

Machine Learning · Computer Science 2021-07-23 Michael E. Sander , Pierre Ablin , Mathieu Blondel , Gabriel Peyré

Network-structured data becomes ubiquitous in daily life and is growing at a rapid pace. It presents great challenges to feature engineering due to the high non-linearity and sparsity of the data. The local and global structure of the…

Machine Learning · Computer Science 2025-01-31 Xin Sun , Zenghui Song , Yongbo Yu , Junyu Dong , Claudia Plant , Christian Boehm

Modern LLMs are increasingly deep, and depth correlates with performance, albeit with diminishing returns. However, do these models use their depth efficiently? Do they compose more features to create higher-order computations that are…

Machine Learning · Computer Science 2025-10-29 Róbert Csordás , Christopher D. Manning , Christopher Potts

Dropout regularization of deep neural networks has been a mysterious yet effective tool to prevent overfitting. Explanations for its success range from the prevention of "co-adapted" weights to it being a form of cheap Bayesian inference.…

Machine Learning · Statistics 2019-05-30 Eric Nalisnick , José Miguel Hernández-Lobato , Padhraic Smyth

Promising resolutions of the generalization puzzle observe that the actual number of parameters in a deep network is much smaller than naive estimates suggest. The renormalization group is a compelling example of a problem which has very…

Machine Learning · Computer Science 2020-12-08 Anita de Mello Koch , Ellen de Mello Koch , Robert de Mello Koch

Normalization layers are critical components of modern AI systems, such as ChatGPT, Gemini, DeepSeek, etc. Empirically, they are known to stabilize training dynamics and improve generalization ability. However, the underlying theoretical…

Machine Learning · Computer Science 2026-02-24 Khoat Than

Training deep neural networks with stochastic gradient descent (SGD) can often achieve zero training loss on real-world tasks although the optimization landscape is known to be highly non-convex. To understand the success of SGD for…

Machine Learning · Statistics 2020-06-15 Yiping Lu , Chao Ma , Yulong Lu , Jianfeng Lu , Lexing Ying

Neural network ensembles have been effectively used to improve generalization by combining the predictions of multiple independently trained models. However, the growing scale and complexity of deep neural networks have led to these methods…

Machine Learning · Computer Science 2024-07-09 Tim Whitaker

Real complex systems are not rigidly structured; no clear rules or blueprints exist for their construction. Yet, amidst their apparent randomness, complex structural properties universally emerge. We propose that an important class of…

All networks can be analyzed at multiple scales. A higher scale of a network is made up of macro-nodes: subgraphs that have been grouped into individual nodes. Recasting a network at higher scales can have useful effects, such as decreasing…

Social and Information Networks · Computer Science 2022-02-18 Ross Griebenow , Brennan Klein , Erik Hoel

We show that the error of iteratively magnitude-pruned networks empirically follows a scaling law with interpretable coefficients that depend on the architecture and task. We functionally approximate the error of the pruned networks,…

Machine Learning · Computer Science 2021-07-06 Jonathan S. Rosenfeld , Jonathan Frankle , Michael Carbin , Nir Shavit

A family of super deep networks, referred to as residual networks or ResNet, achieved record-beating performance in various visual tasks such as image recognition, object detection, and semantic segmentation. The ability to train very deep…

Computer Vision and Pattern Recognition · Computer Science 2019-06-18 Xin Yu , Zhiding Yu , Srikumar Ramalingam

Transformers process tokens in parallel but are temporally shallow: at position $t$, each layer attends to key-value pairs computed based on the previous layer, yielding a depth capped by the number of layers. Recurrent models offer…

Machine Learning · Computer Science 2026-04-24 Costin-Andrei Oncescu , Depen Morwani , Samy Jelassi , Alexandru Meterez , Mujin Kwun , Sham Kakade

Continual learning of deep neural networks is a key requirement for scaling them up to more complex applicative scenarios and for achieving real lifelong learning of these architectures. Previous approaches to the problem have considered…

Machine Learning · Computer Science 2020-06-25 Jary Pomponi , Simone Scardapane , Vincenzo Lomonaco , Aurelio Uncini

The single-layer feedforward neural network with random weights is a recurring motif in the neural networks literature. The advantage of these networks is their simplified training, which reduces to solving a ridge-regression problem. A…

Machine Learning · Computer Science 2025-02-25 M. Andrecut

A long standing open problem in the theory of neural networks is the development of quantitative methods to estimate and compare the capabilities of different architectures. Here we define the capacity of an architecture by the binary…

Machine Learning · Computer Science 2019-03-29 Pierre Baldi , Roman Vershynin

Recent results in the literature indicate that a residual network (ResNet) composed of a single residual block outperforms linear predictors, in the sense that all local minima in its optimization landscape are at least as good as the best…

Machine Learning · Computer Science 2019-10-30 Chulhee Yun , Suvrit Sra , Ali Jadbabaie

Network pruning is one of the most dominant methods for reducing the heavy inference cost of deep neural networks. Existing methods often iteratively prune networks to attain high compression ratio without incurring significant loss in…

Computer Vision and Pattern Recognition · Computer Science 2020-08-17 Duong H. Le , Trung-Nhan Vo , Nam Thoai