Search Results for author:
Found 9 papers, 4 papers with code
Kernel Approximation using Analog In-Memory Computing
We introduce an approach to kernel approximation in machine learning algorithms suitable for mixed-signal Analog In-Memory Computing (AIMC) architectures.
In-Materia Speech Recognition
With the rise of decentralized computing, as in the Internet of Things, autonomous driving, and personalized healthcare, it is increasingly important to process time-dependent signals at the edge efficiently: right at the place where the temporal data are collected, avoiding time-consuming, insecure, and costly communication with a centralized computing facility (or cloud).
AnalogNets: ML-HW Co-Design of Noise-robust TinyML Models and Always-On Analog Compute-in-Memory Accelerator
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.
Adversarial Attacks on Spiking Convolutional Neural Networks for Event-based Vision
Event-based dynamic vision sensors provide very sparse output in the form of spikes, which makes them suitable for low-power applications.
NETWORK INSENSITIVITY TO PARAMETER NOISE VIA PARAMETER ATTACK DURING TRAINING
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
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
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
Our proposed method paves the way towards a system-level implementation of tightly balanced networks on analog mixed-signal neuromorphic hardware.
Ladder Networks for Semi-Supervised Hyperspectral Image Classification
We used the Ladder Network [Rasmus et al. (2015)] to perform Hyperspectral Image Classification in a semi-supervised setting.
