arXiv subjects

Johann Schumann

Publications and source records attributed to Johann Schumann.

5 recordsLinked to original sources

arXiv2026

Non-standard memory models with indexed retrieval

The standard memory models for neural networks are variants of the Hopfield network, where feature representations are stored as vectors in a matrix. Retrieval happens based on similarity between an input vector and the set of stored vectors in a content-addressable manner such that the network evolves towards the closest stored attractor. In other words, the useful property of addressing items in memory directly by index is lost in Hopfield-style neural network models ("associative memory"). In this extended abstract, we present a new model which is extremely simple, derived from biological observation, yet introduces a significant conceptual advance and technical benefits. The goal is to establish adaptivity based on the neuron-centric hypothesis: Plasticity is organized by the neuron which regulates its own synapses. Accordingly we implemented a localist, neuron-centric one-shot learning method and applied it to a simple pattern classification problem (MNIST). We were looking for the existence of high information neurons, to act as indices into the representations. The idea was that we would be able to restore full patterns by indexed retrieval, instead of associative vector retrieval from attractors.

q-bio.NC↗

arXiv2025

On the Practices of Autonomous Systems Development: Survey-based Empirical Findings

Autonomous systems have gained an important role in many industry domains and are beginning to change everyday life. However, due to dynamically emerging applications and often proprietary constraints, there is a lack of information about the practice of developing autonomous systems. This paper presents the first part of the longitudinal study focused on establishing state-of-the-practice, identifying and quantifying the challenges and benefits, identifying the processes and standards used, and exploring verification and validation (V&V) practices used for the development of autonomous systems. The results presented in this paper are based on data about software systems that have autonomous functionality and may employ model-based software engineering (MBSwE) and reuse. These data were collected using an anonymous online survey that was administered in 2019 and were provided by experts with experience in development of autonomous systems and /or the use of MBSwE. Our current work is focused on repeating the survey to collect more recent data and discover how the development of autonomous systems has evolved over time.

cs.SE↗

arXiv2023

Runway Sign Classifier: A DAL C Certifiable Machine Learning System

In recent years, the remarkable progress of Machine Learning (ML) technologies within the domain of Artificial Intelligence (AI) systems has presented unprecedented opportunities for the aviation industry, paving the way for further advancements in automation, including the potential for single pilot or fully autonomous operation of large commercial airplanes. However, ML technology faces major incompatibilities with existing airborne certification standards, such as ML model traceability and explainability issues or the inadequacy of traditional coverage metrics. Certification of ML-based airborne systems using current standards is problematic due to these challenges. This paper presents a case study of an airborne system utilizing a Deep Neural Network (DNN) for airport sign detection and classification. Building upon our previous work, which demonstrates compliance with Design Assurance Level (DAL) D, we upgrade the system to meet the more stringent requirements of Design Assurance Level C. To achieve DAL C, we employ an established architectural mitigation technique involving two redundant and dissimilar Deep Neural Networks. The application of novel ML-specific data management techniques further enhances this approach. This work is intended to illustrate how the certification challenges of ML-based systems can be addressed for medium criticality airborne applications.

cs.LG↗

arXiv2004

Presynaptic modulation as fast synaptic switching: state-dependent modulation of task performance

Neuromodulatory receptors in presynaptic position have the ability to suppress synaptic transmission for seconds to minutes when fully engaged. This effectively alters the synaptic strength of a connection. Much work on neuromodulation has rested on the assumption that these effects are uniform at every neuron. However, there is considerable evidence to suggest that presynaptic regulation may be in effect synapse-specific. This would define a second "weight modulation" matrix, which reflects presynaptic receptor efficacy at a given site. Here we explore functional consequences of this hypothesis. By analyzing and comparing the weight matrices of networks trained on different aspects of a task, we identify the potential for a low complexity "modulation matrix", which allows to switch between differently trained subtasks while retaining general performance characteristics for the task. This means that a given network can adapt itself to different task demands by regulating its release of neuromodulators. Specifically, we suggest that (a) a network can provide optimized responses for related classification tasks without the need to train entirely separate networks and (b) a network can blend a "memory mode" which aims at reproducing memorized patterns and a "novelty mode" which aims to facilitate classification of new patterns. We relate this work to the known effects of neuromodulators on brain-state dependent processing.

cs.NE↗

arXiv2000

Automatic Debugging Support for UML Designs

Design of large software systems requires rigorous application of software engineering methods covering all phases of the software process. Debugging during the early design phases is extremely important, because late bug-fixes are expensive. In this paper, we describe an approach which facilitates debugging of UML requirements and designs. The Unified Modeling Language (UML) is a set of notations for object-orient design of a software system. We have developed an algorithm which translates requirement specifications in the form of annotated sequence diagrams into structured statecharts. This algorithm detects conflicts between sequence diagrams and inconsistencies in the domain knowledge. After synthesizing statecharts from sequence diagrams, these statecharts usually are subject to manual modification and refinement. By using the ``backward'' direction of our synthesis algorithm, we are able to map modifications made to the statechart back into the requirements (sequence diagrams) and check for conflicts there. Fed back to the user conflicts detected by our algorithm are the basis for deductive-based debugging of requirements and domain theory in very early development stages. Our approach allows to generate explanations on why there is a conflict and which parts of the specifications are affected.

cs.SE↗