• Publications
  • Influence
Approximate Computing Methods for Embedded Machine Learning
In this paper, we investigate how approximate computing may reduce the complexity and enable the feasibility of embedded Machine Learning (ML) systems. Expand
  • 11
[Biomechanical study of the ankle joint].
The authors have studied the transmission of body weight in several positions. Two methods have been used - strain gauges and injection of dye into the joint capsules to show areas with contactExpand
  • 8
DCNN for Tactile Sensory Data Classification based on Transfer Learning
Tactile data processing and analysis is still essentially an open challenge. Expand
  • 6
Smart Tactile Sensing Systems Based on Embedded CNN Implementations
This paper presents and compares the implementations of a convolutional neural network model for tactile data decoding on various hardware platforms. Expand
  • 5
  • PDF
Live Demonstration: System based on Electronic Skin and Cutaneous Electrostimulation for Sensory Feedback in Prosthetics
We will show two important aspects of our technology: 1) High sensitivity: light touch detection will be enabled by the high sensitivity of electronic skin (e-skin) prototypes for fingertips, 2) Measuring complex interactions: different contact shapes and multiple contact points will be detected by the commercial e- skin prototype suitable for palm. Expand
  • 1
Energy Efficient Implementation of Machine Learning Algorithms on Hardware Platforms
This paper aims to present an overview about state of the art techniques enabling efficient implementation of Machine and Deep learning (ML/DL) algorithms aiming to improve the energy efficiency. Expand
The Function of Hamstrings: A Pathogenic Hypothesis of Femoropatellar Osteoarthritis
Since the end of the last century there has been controversy concerning the function of the hamstrings. By 1867 Duchenne de Boulogne spoke of a paradoxical action of extension which Lombard (1907)Expand
  • 1
[Biomechanics of lumbar arthrodesis].
  • 2