Joel Z. Leibo

activity

20132026

most citedHuman-level performance in first-person multiplayer games with population-based deep reinforcement learning

693 citations · 3.6k across the 81 of their papers we have counts for

collaborators

Showing 2013Show all

2 papers · 1 filter

cs.CV2013★ 62 cited

Unsupervised Learning of Invariant Representations in Hierarchical Architectures

Fabio Anselmi, Joel Z. Leibo, Lorenzo Rosasco +3

The present phase of Machine Learning is characterized by supervised learning algorithms relying on large sets of labeled examples ( $n \to \infty$ ). The next phase is likely to foc…

cs.CV2013★ 13 cited

Can a biologically-plausible hierarchy effectively replace face detection, alignment, and recognition pipelines?

Qianli Liao, Joel Z Leibo, Youssef Mroueh +1

The standard approach to unconstrained face recognition in natural photographs is via a detection, alignment, recognition pipeline. While that approach has achieved impressive resu…