Boosting RSNNs for long-term memory
Because even spiking neurons deserve a memory boost!
Ismael Balafrej
I work on machine learning across the compute spectrum,
from neuromorphic chips to large-scale training. Based in Montreal.
Recent posts
All posts →Efficient deepfake detection on consumer hardware
Deepfakes are getting smarter; so should detection!
Are electric cars a worse investment?
This post examines the value depreciation of electric vehicles (EV) in the Montreal area, with an analysis of the impact of the Quebec government's decision to phase out the Roulez Vert program on the value.
Unexpected coin flip experiment
In this post, I explore a seemingly straightforward coin flip game between two players. Interestingly, the intuitive approach fails when validated with a Monte Carlo simulation.
What if you could grow an AI chip?
New publication in Nature Communications on electropolymerized dendritic connections for neuromorphic hardware.
PhD thesis defended!
Like a proper nerd, I wore an ECG during my thesis defense. Here is the data!
Recent publications
All papers →Unsupervised local learning based on voltage-dependent synaptic plasticity for resistive and ferroelectric synapses.
Communications Materials (2026)
DOI ↗Enhancing Temporal Learning in Recurrent Spiking Networks for Neuromorphic Applications.
Neuromorphic Computing and Engineering (2025)
DOI ↗Structural Plasticity for Neuromorphic Networks with Electropolymerized Dendritic PEDOT Connections.
Nature Communications (2023)
DOI ↗