no code implementations • 14 Mar 2023 • Jiefeng Chen, Timothy Nguyen, Dilan Gorur, Arslan Chaudhry
We argue that the measure of forward transfer to a task should not be affected by the restrictions placed on the continual learner in order to preserve knowledge of previous tasks.
no code implementations • 1 Feb 2022 • Seyed Iman Mirzadeh, Arslan Chaudhry, Dong Yin, Timothy Nguyen, Razvan Pascanu, Dilan Gorur, Mehrdad Farajtabar
However, in this work, we show that the choice of architecture can significantly impact the continual learning performance, and different architectures lead to different trade-offs between the ability to remember previous tasks and learning new ones.
no code implementations • NeurIPS Workshop ImageNet_PPF 2021 • Huiyi Hu, Ang Li, Daniele Calandriello, Dilan Gorur
We present the One Pass ImageNet (OPIN) problem, which aims to study the effectiveness of deep learning in a streaming setting.
no code implementations • 21 Oct 2021 • Seyed Iman Mirzadeh, Arslan Chaudhry, Dong Yin, Huiyi Hu, Razvan Pascanu, Dilan Gorur, Mehrdad Farajtabar
A primary focus area in continual learning research is alleviating the "catastrophic forgetting" problem in neural networks by designing new algorithms that are more robust to the distribution shifts.
1 code implementation • ICLR 2021 • Seyed Iman Mirzadeh, Mehrdad Farajtabar, Dilan Gorur, Razvan Pascanu, Hassan Ghasemzadeh
Continual (sequential) training and multitask (simultaneous) training are often attempting to solve the same overall objective: to find a solution that performs well on all considered tasks.
no code implementations • NeurIPS 2020 • Nevena Lazic, Dong Yin, Mehrdad Farajtabar, Nir Levine, Dilan Gorur, Chris Harris, Dale Schuurmans
This work focuses on off-policy evaluation (OPE) with function approximation in infinite-horizon undiscounted Markov decision processes (MDPs).
1 code implementation • 7 Feb 2019 • Eric Nalisnick, Akihiro Matsukawa, Yee Whye Teh, Dilan Gorur, Balaji Lakshminarayanan
We propose a neural hybrid model consisting of a linear model defined on a set of features computed by a deep, invertible transformation (i. e. a normalizing flow).
4 code implementations • ICLR 2019 • Eric Nalisnick, Akihiro Matsukawa, Yee Whye Teh, Dilan Gorur, Balaji Lakshminarayanan
A neural network deployed in the wild may be asked to make predictions for inputs that were drawn from a different distribution than that of the training data.
no code implementations • NeurIPS 2009 • Yee W. Teh, Dilan Gorur
The Indian buffet process (IBP) is an exchangeable distribution over binary matrices used in Bayesian nonparametric featural models.
no code implementations • NeurIPS 2008 • Jan Gasthaus, Frank Wood, Dilan Gorur, Yee W. Teh
In this paper we propose a new incremental spike sorting model that automatically eliminates refractory period violations, accounts for action potential waveform drift, and can handle appearance" and "disappearance" of neurons.
no code implementations • NeurIPS 2008 • Dilan Gorur, Yee W. Teh
We propose an efficient sequential Monte Carlo inference scheme for the recently proposed coalescent clustering model (Teh et al, 2008).