Publications related to Does surface completion fail to support uncrowding?

Related publications (20)

Uncovering neural architectures enabling robust and flexible motor control in Drosophila

Uncovering the neural architectures that enable robust and flexible motor control is a fundamental challenge in neuroscience. Understanding the neural circuitry organisation at a cellular level is crucial for advancing our knowledge and developing interven ...

EPFL2025

A new age in protein design empowered by deep learning

Bruno Emanuel Ferreira De Sousa Correia, Michael Bronstein, Casper Alexander Goverde, Arne Schneuing, Hamed Khakzad, Ilia Igashov

The rapid progress in the field of deep learning has had a significant impact on protein design. Deep learning methods have recently produced a breakthrough in protein structure prediction, leading to the availability of high-quality models for millions of ...

Cell Press2023

Using Animal Motion Capture to Learn Neural Representations

Semih Günel

Understanding behavior from neural activity is a fundamental goal in neuroscience. It has practical applications in building robust brain-machine interfaces, human-computer interaction, and assisting patients with neurological disabilities. Despite the eve ...

EPFL2022

Understanding Deep Neural Networks using Adversarial Attacks

Krishna Kanth Nakka

Deep Neural Networks (DNNs) have achieved great success in a wide range of applications, such as image recognition, object detection, and semantic segmentation. Even though the discriminative power of DNNs is nowadays unquestionable, serious concerns have ...

EPFL2022

Multi-layer State Evolution Under Random Convolutional Design

Lenka Zdeborová, Florent Gérard Krzakala

Signal recovery under generative neural network priors has emerged as a promising direction in statistical inference and computational imaging. Theoretical analysis of reconstruction algorithms under generative priors is, however, challenging. For generati ...

2022

A Structured Dictionary Perspective on Implicit Neural Representations

Gizem Yüce, Pascal Frossard, Guillermo Ortiz Jimenez, Beril Besbinar

Implicit neural representations (INRs) have recently emerged as a promising alternative to classical discretized representations of signals. Nevertheless, despite their practical success, we still do not understand how INRs represent signals. We propose a ...

IEEE COMPUTER SOC2022

The Food Recognition Benchmark: Using Deep Learning to Recognize Food in Images

Marcel Salathé, Harris Héritier, Djilani James Kebaili, Victor Guy Boulanger

The automatic recognition of food on images has numerous interesting applications, including nutritional tracking in medical cohorts. The problem has received significant research attention, but an ongoing public benchmark on non-biased (i.e., not scraped ...

FRONTIERS MEDIA SA2022

An Accuracy-Driven Compression Methodology to Derive Efficient Codebook-Based CNNs

David Atienza Alonso, Giovanni Ansaloni, Miguel Peon Quiros, Flavio Ponzina

Codebook-based optimizations are a class of algorithmic-level transformations able to effectively reduce the computing and memory requirements of Convolutional Neural Networks (CNNs). This approach tightly limits the number of unique weights in each layer, ...

2022

Hierarchical graph representations in digital pathology

Jean-Philippe Thiran, Guillaume Jaume

Cancer diagnosis, prognosis, and therapy response predictions from tissue specimens highly depend on the phenotype and topological distribution of constituting histological entities. Thus, adequate tissue representations for encoding histological entities ...

ELSEVIER2022

Selective attention involves a feature-specific sequential release from inhibitory gating

David Pascucci, Gijs Plomp

Selective attention is a fundamental cognitive mechanism that allows our brain to preferentially process relevant sensory information, while filtering out distracting information. Attention is thought to flexibly gate the communication of irrelevant inform ...

2022

Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures

Florent Gérard Krzakala

Despite being the workhorse of deep learning, the backpropagation algorithm is no panacea. It enforces sequential layer updates, thus preventing efficient parallelization of the training process. Furthermore, its biological plausibility is being challenged ...

Curran Associates, Inc.2020

Encoding And Decoding Mixed Bandlimited Signals Using Spiking Integrate-And-Fire Neurons

Martin Vetterli, Adam James Scholefield, Karen Adam

Conventional sampling focuses on encoding and decoding bandlimited signals by recording signal amplitudes at known time points. Alternately, sampling can be approached using biologically-inspired schemes. Among these are integrate-and-fire time encoding ma ...

IEEE2020

Learning Continuous Muscle Control for a Multi-joint Arm by Extending Proximal Policy Optimization with a Liquid State Machine

Marc-Oliver Gewaltig

There have been many advances in the field of reinforcement learning in continuous control problems. Usually, these approaches use deep learning with artificial neural networks for approximation of policies and value functions. In addition, there have been ...

SPRINGER INTERNATIONAL PUBLISHING AG2018

Non-Linear Digital Self-Interference Cancellation for In-Band Full-Duplex Radios Using Neural Networks

Alexios Konstantinos Balatsoukas Stimming

Full-duplex systems require very strong self-interference cancellation in order to operate correctly and a significant part of the self-interference signal is due to non-linear effects created by various transceiver impairments. As such, linear cancellatio ...

IEEE2018

Memory-error tolerance of Scalable and Highly Parallel Architecture for Restricted Boltzmann Machines in Deep Belief Network

Alexandre Schmid

A key aspect of constructing highly scalable Deep-learning microelectronic systems is to implement fault tolerance in the learning sequence. Error-injection analyses for memory is performed using a custom hardware model implementing parallelized restricted ...

Ieee2016

Inference of neuronal network spike dynamics and topology from calcium imaging data

Wulfram Gerstner, Joao Emanuel Felipe Gerhard, Friedemann Zenke

Two-photon calcium imaging enables functional analysis of neuronal circuits by inferring action potential (AP) occurrence ("spike trains") from cellular fluorescence signals. It remains unclear how experimental parameters such as signal-to-noise ratio (SNR ...

Frontiers Research Foundation2013

A Cognitive Reference Based Model for Learning Compositional Hierarchies with Whole-Composite Tags

Ashish Kishore Bindal, Alain Wegmann, Anshuman Bahadur Saxena

A compositional hierarchy is the default organization of knowledge acquired for the purpose of specifying the design requirements of a service. Existing methods for learning compositional hierarchies from natural language text, interpret composition as an ...

2013

Analysis of MLP Based Hierarchical Phoneme Posterior Probability Estimator

Hervé Bourlard, Mathew Magimai Doss, Hynek Hermansky, Joel Praveen Pinto

We analyze a simple hierarchical architecture consisting of two multilayer perceptron (MLP) classifiers in tandem to estimate the phonetic class conditional probabilities. In this hierarchical setup, the first MLP classifier is trained using standard acous ...

2011

Analysis of taste processing in rat gustatory cortex

Riccardo Accolla

Gustatory perception is a complex phenomenon involving the recognition of sensory properties of a food (taste modality and intensity, flavour, texture, fat content, temperature) as well as its reward value (pleasantness and nutritional value). The sense of ...

EPFL2007

Using neural networks to predict slope movements

Laurent Vulliet, Frédéric Mayoraz

1996