62 citations · 129 across the 18 of their papers we have counts for
19 papers
CIPER: Combining Invariant and Equivariant Representations Using Contrastive and Predictive Learning
Xia Xu, Jochen Triesch
Self-supervised representation learning (SSRL) methods have shown great success in computer vision. In recent studies, augmentation-based contrastive learning methods have been pro…
Sequence and Circle: Exploring the Relationship Between Patches
Zhengyang Yu, Jochen Triesch
The vision transformer (ViT) has achieved state-of-the-art results in various vision tasks. It utilizes a learnable position embedding (PE) mechanism to encode the location of each…
Time to augment self-supervised visual representation learning
Arthur Aubret, Markus Ernst, Céline Teulière +1
Biological vision systems are unparalleled in their ability to learn visual representations without supervision. In machine learning, self-supervised learning (SSL) has led to majo…
Degeneracy in epilepsy: Multiple Routes to Hyperexcitable Brain Circuits and their Repair
Tristan Manfred Stöber, Danylo Batulin, Jochen Triesch +2
Developing effective therapies against epilepsy remains a challenge. The complex and multifaceted nature of this disease still fuels controversies about its origin. In this perspec…
Embodied vision for learning object representations
Arthur Aubret, Céline Teulière, Jochen Triesch
Recent time-contrastive learning approaches manage to learn invariant object representations without supervision. This is achieved by mapping successive views of an object onto clo…
Multiple Instance Learning for Brain Tumor Detection from Magnetic Resonance Spectroscopy Data
Diyuan Lu, Gerhard Kurz, Nenad Polomac +3
We apply deep learning (DL) on Magnetic resonance spectroscopy (MRS) data for the task of brain tumor detection. Medical applications often suffer from data scarcity and corruption…
Recurrent Feedback Improves Recognition of Partially Occluded Objects
Markus Roland Ernst, Jochen Triesch, Thomas Burwick
Recurrent connectivity in the visual cortex is believed to aid object recognition for challenging conditions such as occlusion. Here we investigate if and how artificial neural net…
Learning Hierarchical Integration of Foveal and Peripheral Vision for Vergence Control by Active Efficient Coding
Zhetuo Zhao, Jochen Triesch, Bertram E. Shi
The active efficient coding (AEC) framework parsimoniously explains the joint development of visual processing and eye movements, e.g., the emergence of binocular disparity selecti…
Self-Calibrating Active Binocular Vision via Active Efficient Coding with Deep Autoencoders
Charles Wilmot, Bertram E. Shi, Jochen Triesch
We present a model of the self-calibration of active binocular vision comprising the simultaneous learning of visual representations, vergence, and pursuit eye movements. The model…
Learning Abstract Representations through Lossy Compression of Multi-Modal Signals
Charles Wilmot, Gianluca Baldassarre, Jochen Triesch
A key competence for open-ended learning is the formation of increasingly abstract representations useful for driving complex behavior. Abstract representations ignore specific det…
REAL-X -- Robot open-Ended Autonomous Learning Architectures: Achieving Truly End-to-End Sensorimotor Autonomous Learning Systems
Emilio Cartoni, Davide Montella, Jochen Triesch +1
Open-ended learning is a core research field of developmental robotics and AI aiming to build learning machines and robots that can autonomously acquire knowledge and skills increm…
Human-Expert-Level Brain Tumor Detection Using Deep Learning with Data Distillation and Augmentation
Diyuan Lu, Nenad Polomac, Iskra Gacheva +2
The application of Deep Learning (DL) for medical diagnosis is often hampered by two problems. First, the amount of training data may be scarce, as it is limited by the number of p…
Staging Epileptogenesis with Deep Neural Networks
Diyuan Lu, Sebastian Bauer, Valentin Neubert +3
Epilepsy is a common neurological disorder characterized by recurrent seizures accompanied by excessive synchronous brain activity. The process of structural and functional brain a…
Towards Early Diagnosis of Epilepsy from EEG Data
Diyuan Lu, Sebastian Bauer, Valentin Neubert +3
Epilepsy is one of the most common neurological disorders, affecting about 1% of the population at all ages. Detecting the development of epilepsy, i.e., epileptogenesis (EPG), bef…
Recurrent Connectivity Aids Recognition of Partly Occluded Objects
Markus Roland Ernst, Jochen Triesch, Thomas Burwick
Feedforward convolutional neural networks are the prevalent model of core object recognition. For challenging conditions, such as occlusion, neuroscientists believe that the recurr…
Recurrent Connections Aid Occluded Object Recognition by Discounting Occluders
Markus Roland Ernst, Jochen Triesch, Thomas Burwick
Recurrent connections in the visual cortex are thought to aid object recognition when part of the stimulus is occluded. Here we investigate if and how recurrent connections in arti…
Residual Deep Convolutional Neural Network for EEG Signal Classification in Epilepsy
Diyuan Lu, Jochen Triesch
Epilepsy is the fourth most common neurological disorder, affecting about 1% of the population at all ages. As many as 60% of people with epilepsy experience focal seizures which o…
Non-random network connectivity comes in pairs
Felix Z. Hoffmann, Jochen Triesch
Overrepresentation of bidirectional connections in local cortical networks has been repeatedly reported and is in the focus of the ongoing discussion of non-random connectivity. He…
Intrinsically Motivated Learning of Visual Motion Perception and Smooth Pursuit
Chong Zhang, Yu Zhao, Jochen Triesch +1
We extend the framework of efficient coding, which has been used to model the development of sensory processing in isolation, to model the development of the perception/action cycl…