Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Many feedforward neural networks (NNs) generate continuous and piecewise-linear (CPWL) mappings. Specifically, they partition the input domain into regions on which the mapping is affine. The number of these so-called linear regions offers a natural metric ...

Recent developments in neural architecture search (NAS) emphasize the significance of considering robust architectures against malicious data. However, there is a notable absence of benchmark evaluations and theoretical guarantees for searching these robus ...

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...

The desire and ability to place AI-enabled applications on the edge has grown significantly in recent years. However, the compute-, area-, and power-constrained nature of edge devices are stressed by the needs of the AI-enabled applications, due to a gener ...

Topographical disorientation refers to the selective inability to orient oneself in familiar surroundings. However, to date its neural correlates remain poorly understood. Here we use quantitative lesion analysis and a lesion network mapping approach in or ...

This paper presents a comparison of machine learning (ML) methods used for three-dimensional localization of partial discharges (PD) in a power transformer tank. The study examines ML and deep learning (DL) methods, ranging from support vector machines (SV ...

In this paper, we study sampling from a posterior derived from a neural network. We propose a new probabilistic model consisting of adding noise at every pre- and post-activation in the network, arguing that the resulting posterior can be sampled using an ...

Recently, cutting-edge brain-machine interfaces (BMIs) have revealed the potential of decoders such as recurrent neural networks (RNNs) in predicting attempted handwriting [1] or speech [2], enabling rapid communication recovery after paralysis. However, c ...

In the realm of point cloud scene understanding, particularly in indoor scenes, objects are arranged following human habits, resulting in objects of certain semantics being closely positioned and displaying notable inter-object correlations. This can creat ...

Turning pass-through network architectures into iterative ones, which use their own output as input, is a well-known approach for boosting performance. In this paper, we argue that such architectures offer an additional benefit: The convergence rate of the ...

We propose a method for adapting neural networks to distribution shifts at test-time. In contrast to training-time robustness mechanisms that attempt to anticipate and counter the shift, we create a closed-loop system and make use of test-time feedback sig ...

New materials for electrochemical energy storage and conversion are the key to the electrification and sustainable development of our modern societies. Molecular modelling based on the principles of quantum mechanics and statistical mechanics as well as em ...

Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)

Chat with Graph Search

On the number of regions of piecewise linear neural networks

Robust NAS under adversarial training: benchmark, theory, and beyond

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Exploring High-Performance and Energy-Efficient Architectures for Edge AI-Enabled Applications

The neural correlates of topographical disorientation-a lesion analysis study

Partial discharge localization in power transformer tanks using machine learning methods

Gibbs sampling the posterior of neural networks

33.3 MiBMI: A 192/512-Channel 2.46mm² Miniaturized Brain-Machine Interface Chipset Enabling 31-Class Brain-to-Text Conversion Through Distinctive Neural Codes

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

Enabling Uncertainty Estimation in Iterative Neural Networks

Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedback

2023 Roadmap on molecular modelling of electrochemical energy materials