June 2021
·
31 Reads
·
60 Citations
This page lists the scientific contributions of an author, who either does not have a ResearchGate profile, or has not yet added these contributions to their profile.
It was automatically created by ResearchGate to create a record of this author's body of work. We create such pages to advance our goal of creating and maintaining the most comprehensive scientific repository possible. In doing so, we process publicly available (personal) data relating to the author as a member of the scientific community.
If you're a ResearchGate member, you can follow this page to keep up with this author's work.
If you are this author, and you don't want us to display this page anymore, please let us know.
June 2021
·
31 Reads
·
60 Citations
March 2021
·
282 Reads
There have been many successful implementations of neural style transfer in recent years. In most of these works, the stylization process is confined to the pixel domain. However, we argue that this representation is unnatural because paintings usually consist of brushstrokes rather than pixels. We propose a method to stylize images by optimizing parameterized brushstrokes instead of pixels and further introduce a simple differentiable rendering mechanism. Our approach significantly improves visual quality and enables additional control over the stylization process such as controlling the flow of brushstrokes through user input. We provide qualitative and quantitative evaluations that show the efficacy of the proposed parameterized representation.
October 2020
·
26 Reads
·
48 Citations
October 2020
·
13 Reads
·
1 Citation
December 2019
·
130 Reads
We present first experimental results on the novel BrainScaleS-2 neuromorphic architecture based on an analog neuro-synaptic core and augmented by embedded microprocessors for complex plasticity and experiment control. The high acceleration factor of 1000 compared to biological dynamics enables the execution of computationally expensive tasks, by allowing the fast emulation of long-duration experiments or rapid iteration over many consecutive trials. The flexibility of our architecture is demonstrated in a suite of five distinct experiments, which emphasize different aspects of the BrainScaleS-2 system.
March 2019
·
741 Reads
·
120 Citations
Neuromorphic devices represent an attempt to mimic aspects of the brain's architecture and dynamics with the aim of replicating its hallmark functional capabilities in terms of computational power, robust learning and energy efficiency. We employ a single-chip prototype of the BrainScaleS 2 neuromorphic system to implement a proof-of-concept demonstration of reward-modulated spike-timing-dependent plasticity in a spiking network that learns to play a simplified version of the Pong video game by smooth pursuit. This system combines an electronic mixed-signal substrate for emulating neuron and synapse dynamics with an embedded digital processor for on-chip learning, which in this work also serves to simulate the virtual environment and learning agent. The analog emulation of neuronal membrane dynamics enables a 1000-fold acceleration with respect to biological real-time, with the entire chip operating on a power budget of 57 mW. Compared to an equivalent simulation using state-of-the-art software, the on-chip emulation is at least one order of magnitude faster and three orders of magnitude more energy-efficient. We demonstrate how on-chip learning can mitigate the effects of fixed-pattern noise, which is unavoidable in analog substrates, while making use of temporal variability for action exploration. Learning compensates imperfections of the physical substrate, as manifested in neuronal parameter variability, by adapting synaptic weights to match respective excitability of individual neurons.
November 2018
·
344 Reads
Neuromorphic devices represent an attempt to mimic aspects of the brain's architecture and dynamics with the aim of replicating its hallmark functional capabilities in terms of computational power, robust learning and energy efficiency. We employ a single-chip prototype of the BrainScaleS 2 neuromorphic system to implement a proof-of-concept demonstration of reward-modulated spike-timing-dependent plasticity in a spiking network that learns to play the Pong video game by smooth pursuit. This system combines an electronic mixed-signal substrate for emulating neuron and synapse dynamics with an embedded digital processor for on-chip learning, which in this work also serves to simulate the virtual environment and learning agent. The analog emulation of neuronal membrane dynamics enables a 1000-fold acceleration with respect to biological real-time, with the entire chip operating on a power budget of 57mW. Compared to an equivalent simulation using state-of-the-art software, the on-chip emulation is at least one order of magnitude faster and three orders of magnitude more energy-efficient. We demonstrate how on-chip learning can mitigate the effects of fixed-pattern noise, which is unavoidable in analog substrates, while making use of temporal variability for action exploration. Learning compensates imperfections of the physical substrate, as manifested in neuronal parameter variability, by adapting synaptic weights to match respective excitability of individual neurons.
... For the content constraint, the gap of pixel values is narrowed between the generated image and the content image, and finally, the desired image is obtained. There are three types of style transfer methods based on the number of styles the model can transfer: Per-Style-Per-Model [1][2][3][4][5][6][7][8], Multiple-Style-Per-Model [9][10][11][12], and Arbitrary-Style-Per-Model . In the above method, the Per-Style-Per-Model method can achieve excellent style transfer, but only one style can be transferred and needs to be retrained when facing new styles. ...
June 2021
... Furthermore, spike latency codes may also provide benefits over conventional rate-based communication (Göltz et al. 2021a, b), but their scalability to large-scale applications still needs to be explored. And, specifically for analog neuromorphic substrates, the physical emulation of relevant dynamics as opposed to their simulation by an arithmetic logic unit can also yield benefits in terms of energy consumption and speed (Billaudelle et al. 2020). Due to these advantages, large-scale brain-inspired AI substrates have the potential of being operable at a significantly reduced cost compared to conventional GPU clusters, thus democratizing the ownership and use of competitive AI hardware. ...
October 2020
... The SNNs are based on spiking neurons that model rigorously the physiology of the neural cells in the brain. The hardware implementation of the SNN benefits from fast response, low power consumption, and a very good signal-to-noise ratio [1], which makes SNN a good candidate for the implementation of control units of robotic systems. In robotic systems, motion is of high importance because it provides the robots with the ability to interact mechanically with the environment. ...
March 2019