Search Results for author: Julian Büchel

Found 7 papers, 1 papers with code

AnalogNets: ML-HW Co-Design of Noise-robust TinyML Models and Always-On Analog Compute-in-Memory Accelerator

no code implementations10 Nov 2021 Chuteng Zhou, Fernando Garcia Redondo, Julian Büchel, Irem Boybat, Xavier Timoneda Comas, S. R. Nandakumar, Shidhartha Das, Abu Sebastian, Manuel Le Gallo, Paul N. Whatmough

We also describe AON-CiM, a programmable, minimal-area phase-change memory (PCM) analog CiM accelerator, with a novel layer-serial approach to remove the cost of complex interconnects associated with a fully-pipelined design.

Keyword Spotting

Adversarial Attacks on Spiking Convolutional Networks for Event-based Vision

no code implementations6 Oct 2021 Julian Büchel, Gregor Lenz, Yalun Hu, Sadique Sheik, Martino Sorbaro

Spiking neural networks work well with the sparse nature of event-based data and suit deployment on low-power neuromorphic hardware.

Adversarial Attack Event-based vision

NETWORK INSENSITIVITY TO PARAMETER NOISE VIA PARAMETER ATTACK DURING TRAINING

no code implementations ICLR 2022 Julian Büchel, Fynn Firouz Faber, Dylan Richard Muir

We present a new network training algorithm that attacks network parameters during training, and promotes robust performance during inference in the face of random parameter variation.

Network insensitivity to parameter noise via adversarial regularization

2 code implementations9 Jun 2021 Julian Büchel, Fynn Faber, Dylan R. Muir

We present a new adversarial network optimisation algorithm that attacks network parameters during training, and promotes robust performance during inference in the face of parameter variation.

Supervised training of spiking neural networks for robust deployment on mixed-signal neuromorphic processors

no code implementations12 Feb 2021 Julian Büchel, Dmitrii Zendrikov, Sergio Solinas, Giacomo Indiveri, Dylan R. Muir

Our method provides robust deployment of pre-trained networks on mixed-signal neuromorphic hardware, without requiring per-device training or calibration.

Implementing efficient balanced networks with mixed-signal spike-based learning circuits

no code implementations27 Oct 2020 Julian Büchel, Jonathan Kakon, Michel Perez, Giacomo Indiveri

Our proposed method paves the way towards a system-level implementation of tightly balanced networks on analog mixed-signal neuromorphic hardware.

Edge-computing

Ladder Networks for Semi-Supervised Hyperspectral Image Classification

no code implementations4 Dec 2018 Julian Büchel, Okan Ersoy

We used the Ladder Network [Rasmus et al. (2015)] to perform Hyperspectral Image Classification in a semi-supervised setting.

Classification General Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.