41 citations · 64 across the 5 of their papers we have counts for
5 papers
Investigating Trade-offs in Utility, Fairness and Differential Privacy in Neural Networks
Marlotte Pannekoek, Giacomo Spigler
To enable an ethical and legal use of machine learning algorithms, they must both be fair and protect the privacy of those whose data are being used. However, implementing privacy…
Flatland-RL : Multi-Agent Reinforcement Learning on Trains
Sharada Mohanty, Erik Nygren, Florian Laurent +11
Efficient automated scheduling of trains remains a major challenge for modern railway systems. The underlying vehicle rescheduling problem (VRSP) has been a major focus of Operatio…
Meta-learnt priors slow down catastrophic forgetting in neural networks
Giacomo Spigler
Current training regimes for deep learning usually involve exposure to a single task / dataset at a time. Here we start from the observation that in this context the trained model…
The Temporal Singularity: time-accelerated simulated civilizations and their implications
Giacomo Spigler
Provided significant future progress in artificial intelligence and computing, it may ultimately be possible to create multiple Artificial General Intelligences (AGIs), and possibl…
Denoising Autoencoders for Overgeneralization in Neural Networks
Giacomo Spigler
Despite the recent developments that allowed neural networks to achieve impressive performance on a variety of applications, these models are intrinsically affected by the problem…