no code implementations • 26 Feb 2018 • Ershad Banijamali, Yasin Abbasi-Yadkori, Mohammad Ghavamzadeh, Nikos Vlassis
However, under a condition that is akin to the occupancy measures of the base policies having large overlap, we show that there exists an efficient algorithm that finds a policy that is almost as good as the best convex combination of the base policies.
no code implementations • 15 Oct 2017 • Ershad Banijamali, Rui Shu, Mohammad Ghavamzadeh, Hung Bui, Ali Ghodsi
We also propose a principled variational approximation of the embedding posterior that takes the future observation into account, and thus, makes the variational approximation more robust against the noise.
no code implementations • 24 Nov 2017 • Ershad Banijamali, Ahmad Khajenezhad, Ali Ghodsi, Mohammad Ghavamzadeh
In this paper, We study the problem of learning a controllable representation for high-dimensional observations of dynamical systems.
no code implementations • 24 Nov 2017 • Ershad Banijamali, Amir-Hossein Karimi, Alexander Wong, Ali Ghodsi
The problem of feature disentanglement has been explored in the literature, for the purpose of image and video processing and text analysis.
no code implementations • 7 Apr 2017 • Ershad Banijamali, Ali Ghodsi
Spectral clustering is a powerful clustering algorithm that suffers from high computational complexity, due to eigen decomposition.
no code implementations • 10 Feb 2017 • Ershad Banijamali, Ali Ghodsi, Pascal Poupart
The model consists of K networks that are trained together to learn the underlying distribution of a given data set.
no code implementations • 16 Sep 2016 • Mina Nouredanesh, H. R. Tizhoosh, Ershad Banijamali, James Tung
The objective of this paper is to harness the potentials of both Gabor and Radon transforms in order to introduce expressive binary features, called barcodes, for image annotation/tagging tasks.
no code implementations • 10 May 2016 • Ershad Banijamali, Ali Ghodsi
Then, we map the data to lower-dimensional space using a linear transformation such that the dependency between the transformed data and the assigned labels is maximized.
no code implementations • 14 May 2016 • Mina Nouredanesh, Hamid. R. Tizhoosh, Ershad Banijamali
This has significantly heightened the need for automated annotation of the images on one side, and fast and memory-efficient content-based image retrieval systems on the other side.
no code implementations • 18 Dec 2018 • Ershad Banijamali, Amir-Hossein Karimi, Ali Ghodsi
We consider the problem of sufficient dimensionality reduction (SDR), where the high-dimensional observation is transformed to a low-dimensional sub-space in which the information of the observations regarding the label variable is preserved.
no code implementations • ICCV 2021 • Ershad Banijamali, Mohsen Rohani, Elmira Amirloo, Jun Luo, Pascal Poupart
In autonomous driving (AD), accurately predicting changes in the environment can effectively improve safety and comfort.
no code implementations • CVPR 2021 • Elmira Amirloo, Mohsen Rohani, Ershad Banijamali, Jun Luo, Pascal Poupart
While supervised learning is widely used for perception modules in conventional autonomous driving solutions, scalability is hindered by the huge amount of data labeling needed.
no code implementations • ICLR 2022 • Ershad Banijamali
Inferring interactions among entities is an important problem in studying dynamicalsystems, which greatly impacts the performance of downstream tasks, such asprediction.