Computational complexity of deep learning: fundamental limitations and empirical phenomena

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Deep learning has brought incredible progress in areas where traditional algorithms struggle. It can be because they need rules that are sometimes hard to conceptualize, it can also be that the number and manner of combining these rules are too complex to ...

Recent advancements in deep learning have found compelling applications in the image-based inspection of infrastructure systems. However, the efficacy of these models hinges significantly on the quality and diversity of the input data used for training. In ...

Determining whether a molecule can be synthesized is crucial in chemistry and drug discovery, as it guides experimental prioritization and molecule ranking in de novo design tasks. Existing scoring approaches to assess synthetic feasibility struggle to ext ...

Non-Bayesian social learning is a framework for distributed hypothesis testing aimed at learning the true state of the environment. Traditionally, the agents are assumed to receive observations conditioned on the same true state, although it is also possib ...

Nodal properties are of particular importance when investigating patterns in brain networks. Nodal information is usually studied by comparing a few nodal measurements (up to three), resulting in analyses in three-dimensional spaces, at maximum. We offer a ...

Extensive research has been conducted on fault diagnosis of planetary gearboxes using vibration signals and deep learning (DL) approaches. However, DL-based methods are susceptible to the domain shift problem caused by varying operating conditions of the g ...

We address the problem of segmenting anomalies and unusual obstacles in road scenes for the purpose of self-driving safety. The objects in question are not present in the common training sets as it is not feasible to collect and annotate examples for every ...

Current post-earthquake damage assessment methodologies are not only time-consuming but also subjective in nature and difficult to document. Recent advancements in artificial intelligence and technological devices make it possible to accomplish this task a ...

Objective. Powered lower-limb prostheses relying on decoding motor intentions from non-invasive sensors, like electromyographic (EMG) signals, can significantly improve the quality of life of amputee subjects. However, the optimal combination of high decod ...

In this account, we discuss the use of genetic algorithms in the inverse design process of homogeneous catalysts for chemical transformations. We describe the main components of evolutionary experiments, specifically the nature of the fitness function to o ...

Our transportation field has recently witnessed an arms race of neural network-based trajectory predictors. While these predictors are at the core of many applications such as autonomous navigation or pedestrian flow simulations, their adversarial robustne ...

Automatic speech recognition (ASR) allows transcribing the communications between air traffic controllers (ATCOs) and aircraft pilots. The transcriptions are used later to extract ATC named entities, e.g., aircraft callsigns. One common challenge is speech ...

Progress in computing capabilities has enhanced science in many ways. In recent years, various branches of machine learning have been the key facilitators in forging new paths, ranging from categorizing big data to instrumental control, from materials desi ...

Objective. Optic nerve's intraneural stimulation is an emerging neuroprosthetic approach to provide artificial vision to totally blind patients. An open question is the possibility to evoke individual non-overlapping phosphenes via selective intraneural op ...

We provide an introduction to Gaussian process regression (GPR) machinelearning methods in computational materials science and chemistry. The focus of the present review is on the regression of atomistic properties: in particular, on the construction of in ...

Structural Health Monitoring (SHM) has greatly benefited from computer vision. Recently, deep learning approaches are widely used to accurately estimate the state of deterioration of infrastructure. In this work, we focus on the problem of bridge surface s ...

Making decisions is part and parcel of being human. Among a set of actions, we want to choose the one that has the highest reward. But the uncertainty of the outcome prevents us from always making the right decision. Making decisions under uncertainty can ...

In social learning, agents form their opinions or beliefs about certain hypotheses by exchanging local information. This work considers the recent paradigm of weak graphs, where the network is partitioned into sending and receiving components, with the for ...

We propose a new benchmarking protocol to evaluate algorithms for bimanual robotic manipulation semi-deformable objects. The benchmark is inspired from two real-world applications: (a) watchmaking craftsmanship, and (b) belt assembly in automobile engines. ...

Computational complexity of deep learning: fundamental limitations and empirical phenomena

Chattez avec Graph Search

Extending Capabilities of Attention-based Models

Uncertainty quantification for a deep learning models for image-based crack segmentation

FSscore: A Personalized Machine Learning-Based Synthetic Feasibility Score

Detection of Malicious Agents in Social Learning

Connectome embedding in multidimensional graph spaces

Domain knowledge-informed synthetic fault sample generation with health data map for cross-domain planetary gearbox fault diagnosis

Detecting Anomalies and Obstacles in Road Scenes

Automated post-earthquake damage assessment of stone masonry buildings integrating machine learning, computer vision, and physics-based modeling

Early decoding of walking tasks with minimal set of EMG channels

Genetic Algorithms for the Discovery of Homogeneous Catalysts

Are socially-aware trajectory prediction models really socially-aware?

Bertraffic: Bert-Based Joint Speaker Role And Speaker Change Detection For Air Traffic Control Communications

A data-driven approach for lightning nowcasting with deep learning

The role of convolutional neural networks in scanning probe microscopy: a review

A machine-learning algorithm correctly classifies cortical evoked potentials from both visual stimulation and electrical stimulation of the optic nerve

Gaussian Process Regression for Materials and Molecules

Vision based pixel-level bridge structural damage detection using a link ASPP network

Multi-armed Bandits in Action

Learning Graph Influence From Social Interactions

Benchmark for Bimanual Robotic Manipulation of Semi-deformable Objects