Lambert Schomaker

University of Groningen | RUG · Institute of Artificial Intelligence and Cognitive Engineering (Alice)

This study introduced a framework for smart HVAC controllers that can be used at scale. The proposed controllers derive their control policy solely from data. First a simulator of the process is learned, which we call the Neural Twin. The results showed that the Neural Twin framework is able to simulate several distinct processes with an average ab...

Background: A DPP6 gene risk haplotype, putatively enhancing Purkinje fiber transient outward current Ito, associates with familial idiopathic ventricular fibrillation (IVF). Outside this genetic disposition, no clinical risk factors nor ECG features for IVF have so far been identified to recognize those at risk for IVF. Objective: We aimed to deve...

In this paper, we concentrate on the text-to-image synthesis task that aims at automatically producing perceptually realistic pictures from text descriptions. Recently, several single-stage methods have been proposed to deal with the problems of a more complicated multi-stage modular architecture. However, they often suffer from the lack-of-diversi...

Recognition of Off-line Chinese characters is still a challenging problem, especially in historical documents, not only in the number of classes extremely large in comparison to contemporary image retrieval methods, but also new unseen classes can be expected under open learning conditions (even for CNN). Chinese character recognition with zero or...

In an era characterized by the rapid growth of data processing, developing new and efficient data processing technologies has become a priority. We address this by proposing a novel type of neuromorphic technology we call Fused-MemBrain. Our proposal is inspired by Golgi's theory modeling the brain as a syncytial continuum, in contrast to Cajal's t...

In reinforcement learning, reward shaping is an efficient way to augment the reward signal, so to guide the learning process of an agent. A well-known reward shaping framework is the potential based reward shaping (PBRS) framework, which uses a so-called potential function to guarantee the policy invariance after reward shaping, to prevent undesira...

Current research in robotics is mainly focused on implementing the primary functionality. However, really autonomous systems require more than that. For robustness, fault tolerance and sustained deployability, self maintenance - as is prevalent in biological systems - is needed too. This has implications for cyber-physical systems in industry too....

Work presentation at the CogniGron center for neuromorphic computing, September 16th, 2024 Abstract The term 'memory' is easily used in many of the discussions in our multidisciplinary center (physics, AI, mathematics, computer science, cognitive science). The advent of computers has led to a dominant interpretation of what 'memory' is about. Sti...

This work computationally investigates an algorithm that was originally proposed for creating and searching trees of patterns under the assumption that it seeks the most efficient internal representation of the external world, namely a real-world dataset of patterns. The algorithm produces a transition from star graph to regular 1d lattice, passing...

Determining the chronology of ancient handwritten manuscripts is essential for reconstructing the evolution of ideas. For the Dead Sea Scrolls, this is particularly important. However, there is an almost complete lack of date-bearing manuscripts evenly distributed across the timeline and written in similar scripts available for palaeographic compar...

Nanostructured zirconia and gold films (ns-Au/ZrO x ) have been demonstrated as devices characterized by non-linear and hysteretic electrical behavior, with short-term memory and potentiation/depression activity. Here we investigate the conduction mechanisms regulating the non-linear behavior of the nanostructured bilayer Au/ZrO x films. In particu...

Predictive maintenance is a maintenance policy where the goal is to detect potential future maintenance risks in a system so that the maintenance process can be optimised before system faults occur. This paper describes a deep learning model that does not require domain expertise. Deep learning approaches have several benefits over explicit statist...

One of the main questions paleographers aim to answer while studying historical manuscripts is when they were produced. Automatized methods provide tools that can aid in a more accurate and objective date estimation. Many of these methods are based on the hypothesis that handwriting styles change over periods. However, the sparse availability of di...

The goal of a speech-to-image transform is to produce a photo-realistic picture directly from a speech signal. Current approaches are based on a stacked modular framework that suffers from three vital issues: (1) Training separate networks is time-consuming, inefficient and the convergence of the final generative model depends on the previous gener...

Valedictory lecture of prof. dr. Lambert Schomaker, in the Doopsgezinde Kerk, Groningen, on March 8th, 2024. Video recording with English subtitles, accompanying slides as Powerpoint and PDF file. Afternoon program (presentations by colleagues and PhD students were in the morning session). 00:00:00 Opening by prof. Raffaella Carloni 00:00:36 pr...

Classifying ancient manuscripts based on their writing surfaces often becomes essential for palaeographic research, including writer identification, manuscript localization, date estimation, and, occasionally, forgery detection. Researchers continually perform corroborative tests to classify manuscripts based on physical materials. However, these t...

A compact and tractable two-dimensional model to generate the topological network structure of domain walls in BiFeO 3 thin films is presented in this study. Our method combines the stochastic geometry parametric model of the centroidal Voronoi tessellation optimized using the von Neumann entropy, a novel information-theoretic tool for networks. Th...

This paper leverages the OpenSim physics-based simulation environment for the forward dynamic simulation of an osseointegrated transfemoral amputee musculoskeletal model, wearing a generic prosthesis. A deep reinforcement learning architecture, which combines the proximal policy optimization algorithm with imitation learning, is designed to enable...

Text-to-image generation intends to automatically produce a photo-realistic image, conditioned on a textual description. To facilitate the real-world applications of text-to-image synthesis, we focus on studying the following three issues: (1) How to ensure that generated samples are believable, realistic or natural? (2) How to exploit the latent s...

Image of announcement of colloquium on generative artificial intelligence by Tijn van der Zant around the time of finishing his dissertation with the same title.

High-quality and representative data is essential for both Imitation Learning (IL)- and Reinforcement Learning (RL)-based motion planning tasks. For real robots, it is challenging to collect enough qualified data either as demonstrations for IL or experiences for RL due to safety consideration in environments with obstacles. We target this challeng...

Automatic assessment of the quality of scholarly documents is a difficult task with high potential impact. Multimodality, in particular the addition of visual information next to text, has been shown to improve the performance on scholarly document quality prediction (SDQP) tasks. We propose the multimodal predictive model MultiSChuBERT. It combine...

Steepness curves (.png) for PCCL curriculum learning. The curriculum can vary from convex, to linear, to concave, representing teacher criticality. This method was also used in determining the 'temperature T' curve in training Kohonen self-organized maps: L. Schomaker and M. Bulacu, “Automatic writer identification using connected-component contou...

To build neuromorphic hardware with self-assembled memristive networks, it is necessary to determine how the functional connectivity between electrodes can be adjusted, under the application of external signals. In this work we analyse a model of a disordered memristor-resistor network, within the framework of graph theory. Such a model is well sui...

Handwriting recognition has seen significant success with the use of deep learning. However, a persistent shortcoming of neural networks is that they are not well-equipped to deal with shifting data distributions. In the field of handwritten text recognition (HTR), this shows itself in poor recognition accuracy for writers that are not similar to t...

High-quality and representative data is essential for both Imitation Learning (IL)- and Reinforcement Learning (RL)-based motion planning tasks. For real robots, it is challenging to collect enough qualified data either as demonstrations for IL or experiences for RL due to safety considerations in environments with obstacles. We target this challen...

Current paradigms for neuromorphic computing focus on internal computing mechanisms, for instance using spiking-neuron models. In this study, we propose to exploit what is known about neuro-mechanical control, exploiting the mechanisms of neural ensembles and recruitment, combined with the use of second-order overdamped impulse responses correspond...

The goal of a speech-to-image transform is to produce a photo-realistic picture directly from a speech signal. Recently, various studies have focused on this task and have achieved promising performance. However, current speech-to-image approaches are based on a stacked modular framework that suffers from three vital issues: 1) Training separate ne...

In recent years, deep learning (DL) has achieved impressive successes in many application domains, including Handwritten-Text Recognition. However, DL methods demand a long training process and a huge amount of human-based labeled data. To address these issues, we explore several label-free heuristics for detecting the early-stopping point in train...

The interest in the use of organoids in the biomedical field has increased exponentially in the past years. Organoids, or three-dimensional “mini-organs”, have the ability to proliferate and self-organize in-vitro, while displaying varying morphologies. When in culture, these structures can overlap with each other making the quantification and morp...

Researchers continually perform corroborative tests to classify ancient historical documents based on the physical materials of their writing surfaces. However, these tests, often performed on-site, requires actual access to the manuscript objects. The procedures involve a considerable amount of time and cost, and can damage the manuscripts. Develo...

The goal of a speech-to-image transform is to produce a photo-realistic picture directly from a speech signal. Recently, various studies have focused on this task and have achieved promising performance. However, current speech-to-image approaches are based on a stacked modular framework that suffers from three vital issues: 1) Training separate ne...

We present the OrganelX e-Science Web Server that provides a user-friendly implementation of the In-Pero and In-Mito classifiers for sub-peroxisomal and sub-mitochondrial localization of peroxisomal and mitochondrial proteins and the Is-PTS1 algorithm for detecting and validating potential peroxisomal proteins carrying a PTS1 signal sequence. The O...

This paper focuses on the classification of seven locomotion modes (sitting, standing, level ground walking, ramp ascent and descent, stair ascent and descent), the transitions among these modes, and the gait phases within each mode, by only using data in the frequency domain from one or two inertial measurement units. Different deep neural network...

Electronic conduction along individual domain walls (DWs) is reported in BiFeO3 (BFO) and other nominally insulating ferroelectrics. DWs in these materials separate regions of differently oriented electrical polarization (domains) and are just a few atoms wide, providing self‐assembled nanometric conduction paths. Herein, it is shown that electroni...

This presentation (CogniGron internal discussion) presents a number of comments on the notion of 'criticality' in biological and neuromorphic systems. Although the mathematical tools surrounding order-based system description are highly insightful and useful, there is a danger that special qualities are being attributed to the 'critical' state of a...

The task of text-to-image generation has achieved remarkable progress due to the advances in conditional generative adversarial networks (GANs). However, existing conditional text-to-image GANs approaches mostly concentrate on improving both image quality and semantic relevance but ignore the explainability of the model which plays a vital role in...

Electronic conduction along individual domain walls (DWs) has been reported in BiFeO$_3$ (BFO) and other nominally insulating ferroelectrics. DWs in these materials separate regions of differently oriented electrical polarization (domains) and are just a few atoms wide, providing self-assembled nanometric conduction paths. In this work, it is shown...

Computational approaches for sub-organelle protein localisation and identification are often neglected while general methods, not suitable for specific use cases, are promoted instead. In particular, organelle-specific research lacks user-friendly and easily accessible computational tools that allow researchers to perform computational analysis bef...

Although the performance of current automatic recognition algorithms of on-line handwriting has much improved in recent years, there are still many problems with the actual application of these systems. It appears that the step from academical experiments to real-life use of such algorithms, in, e.g., portable pen computers, is still difficult. Wha...

The necessity for cataloguing Western handwriting styles becomes more and more apparent as online handwriting recognition algorithms currently reach an asymptote in their performance, and a limited generalization from laboratory training set to real life conditions is observed. Although the algorithms as such still need to be refined, and an optima...

Background: A DPP6 gene risk haplotype, putatively enhancing Purkinje fiber transient outward current I to , associates with familial idiopathic ventricular fibrillation (IVF). Outside this genetic disposition, no clinical risk factors nor ECG features for IVF have so far been identified to recognize those at risk for IVF. Objective: We aimed to de...

The task of text-to-image generation has achieved remarkable progress due to the advances in the conditional generative adversarial networks (GANs). However, existing conditional text-to-image GANs approaches mostly concentrate on improving both image quality and semantic relevance but ignore the explainability of the model which plays a vital role...

Researchers continually perform corroborative tests to classify ancient historical documents based on the physical materials of their writing surfaces. However, these tests, often performed on-site, requires actual access to the manuscript objects. The procedures involve a considerable amount of time and cost, and can damage the manuscripts. Develo...

Text-to-image generation intends to automatically produce a photo-realistic image, conditioned on a textual description. It can be potentially employed in the field of art creation, data augmentation, photo-editing, etc. Although many efforts have been dedicated to this task, it remains particularly challenging to generate believable, natural scene...

Labeling data can be an expensive task as it is usually performed manually by domain experts. This is cumbersome for deep learning, as it is dependent on large labeled datasets. Active learning (AL) is a paradigm that aims to reduce labeling effort by only using the data which the used model deems most informative. Little research has been done on...

In recent years, an enormous amount of fluorescence microscopy images were collected in high-throughput lab settings. Analyzing and extracting relevant information from all images in a short time is almost impossible. Detecting tiny individual cell compartments is one of many challenges faced by biologists. This paper aims at solving this problem b...

Word embeddings are used as building blocks for a wide range of natural language processing and information retrieval tasks. These embeddings are usually represented as continuous vectors, requiring significant memory capacity and computationally expensive similarity measures. In this study, we introduce a novel method for semantic hashing continuo...

In this paper, we present an efficient and effective single-stage framework (DiverGAN) to generate diverse, plausible and semantically consistent images according to a natural-language description. DiverGAN adopts two novel word-level attention modules, i.e., a channel-attention module (CAM) and a pixel-attention module (PAM), which model the impor...

Labeling data can be an expensive task as it is usually performed manually by domain experts. This is cumbersome for deep learning, as it is dependent on large labeled datasets. Active learning (AL) is a paradigm that aims to reduce labeling effort by only using the data which the used model deems most informative. Little research has been done on...

Reward shaping is an efficient way to incorporate domain knowledge into a reinforcement learning agent. Nevertheless , it is unpractical and inconvenient to require prior knowledge for designing shaping rewards. Therefore, learning the shaping reward function by the agent during training could be more effective. In this paper, based on the potentia...

Most existing text-to-image generation methods adopt a multi-stage modular architecture which has three significant problems: 1) Training multiple networks increases the run time and affects the convergence and stability of the generative model; 2) These approaches ignore the quality of early-stage generator images; 3) Many discriminators need to b...

Imitation learning (IL) enables robots to acquire skills quickly by transferring expert knowledge, which is widely adopted in reinforcement learning (RL) to initialize exploration. However, in long-horizon motion planning tasks, a challenging problem in deploying IL and RL methods is how to generate and collect massive, broadly distributed data suc...

Document binarization is a key step in most document analysis tasks. However, historical-document images usually suffer from various degradations, making this a very challenging processing stage. The performance of document image binarization has improved dramatically in recent years by the use of Convolutional Neural Networks (CNNs). In this paper...

The Dead Sea Scrolls are tangible evidence of the Bible’s ancient scribal culture. This study takes an innovative approach to palaeography—the study of ancient handwriting—as a new entry point to access this scribal culture. One of the problems of palaeography is to determine writer identity or difference when the writing style is near uniform. Thi...

This paper presents an end-to-end neural network system to identify writers through handwritten word images, which jointly integrates global-context information and a sequence of local fragment-based features. The global-context information is extracted from the tail of the neural network by a global average pooling step. The sequence of local and...

In recent years, an enormous amount of fluorescence microscopy images were collected in high-throughput lab settings. Analyzing and extracting relevant information from all images in a short time is almost impossible. Detecting tiny individual cell compartments is one of many challenges faced by biologists. This paper aims at solving this problem b...

This paper presents an end-to-end neural network system to identify writers through handwritten word images, which jointly integrates global-context information and a sequence of local fragment-based features. The global-context information is extracted from the tail of the neural network by a global average pooling step. The sequence of local and...

Imitation learning (IL) enables robots to acquire skills quickly by transferring expert knowledge, which is widely adopted in reinforcement learning (RL) to initialize exploration. However, in long-horizon motion planning tasks, a challenging problem in deploying IL and RL methods is how to generate and collect massive, broadly distributed data suc...

In Reinforcement learning, Q-learning is the best-known algorithm but it suffers from overestimation bias, which may lead to poor performance or unstable learning. In this paper, we present a novel analysis of this problem using various control tasks. For solving these tasks, Q-learning is combined with a multilayer perceptron (MLP), experience rep...

The strength of long short-term memory neural networks (LSTMs) that have been applied is more located in handling sequences of variable length than in handling geometric variability of the image patterns. In this paper, an end-to-end convolutional LSTM neural network is used to handle both geometric variation and sequence variability. The best resu...

In this paper, we propose a two-stage learning framework for visual navigation in which the experience of the agent during exploration of one goal is shared to learn to navigate to other goals. We train a deep neural network for estimating the robot’s position in the environment using ground truth information provided by a classical localization an...

Predicting the number of citations of scholarly documents is an upcoming task in scholarly document processing. Besides the intrinsic merit of this information, it also has a wider use as an imperfect proxy for quality which has the advantage of being cheaply available for large volumes of scholarly documents. Previous work has dealt with number of...

Presentation given at the CogniGron Center in the CogniGron@Work series 18/12/2020 How to bridge the gap between current deep learning and current neuromorphic computing? Lambert Schomaker Abstract ›It has become clear that the researchers in neuromorphic computing focus on training methods for multi-layer perceptrons pointing to a large numbe...

Most existing text-to-image generation methods adopt a multi-stage modular architecture which has three significant problems: (1) Training multiple networks can increase the run time and affect the convergence and stability of the generative model; (2) These approaches ignore the quality of early-stage generator images; (3) Many discriminators need...

This paper presents CentroidNetV2, a novel hybrid Convolutional Neural Network (CNN) that has been specifically designed to segment and count many small and connected object instances. This complete redesign of the original CentroidNet uses a CNN backbone to regress a field of centroid-voting vectors and border-voting vectors. The segmentation mask...

The Dead Sea Scrolls are tangible evidence of the Bible's ancient scribal culture. Palaeography - the study of ancient handwriting - can provide access to this scribal culture. However, one of the problems of traditional palaeography is to determine writer identity when the writing style is near uniform. This is exemplified by the Great Isaiah Scro...