no code implementations • 12 Feb 2021 • Yuhong Song, Weiwen Jiang, Bingbing Li, Panjie Qi, Qingfeng Zhuge, Edwin Hsing-Mean Sha, Sakyasingha Dasgupta, Yiyu Shi, Caiwen Ding
Specifically, RT3 integrates two-level optimizations: First, it utilizes an efficient BP as the first-step compression for resource-constrained mobile devices; then, RT3 heuristically generates a shrunken search space based on the first level optimization and searches multiple pattern sets with diverse sparsity for PP via reinforcement learning to support lightweight software reconfiguration, which corresponds to available frequency levels of DVFS (i. e., hardware reconfiguration).
no code implementations • 1 Jan 2021 • Qing Lu, Weiwen Jiang, Meng Jiang, Jingtong Hu, Sakyasingha Dasgupta, Yiyu Shi
The success of gragh neural networks (GNNs) in the past years has aroused grow-ing interest and effort in designing best models to handle graph-structured data.
1 code implementation • 17 Jul 2020 • Weiwen Jiang, Lei Yang, Sakyasingha Dasgupta, Jingtong Hu, Yiyu Shi
To tackle this issue, HotNAS builds a chain of tools to design hardware to support compression, based on which a global optimizer is developed to automatically co-search all the involved search spaces.
no code implementations • 1 Aug 2019 • Dan Teng, Sakyasingha Dasgupta
In order to mimic the human ability of continual acquisition and transfer of knowledge across various tasks, a learning system needs the capability for continual learning, effectively utilizing the previously acquired skills.
1 code implementation • 6 Jul 2019 • Weiwen Jiang, Lei Yang, Edwin Sha, Qingfeng Zhuge, Shouzhen Gu, Sakyasingha Dasgupta, Yiyu Shi, Jingtong Hu
We propose a novel hardware and software co-exploration framework for efficient neural architecture search (NAS).
no code implementations • 25 Jan 2019 • Pengqian Yu, Joon Sern Lee, Ilya Kulyatin, Zekun Shi, Sakyasingha Dasgupta
Dynamic portfolio optimization is the process of sequentially allocating wealth to a collection of assets in some consecutive trading periods, based on investors' return-risk profile.
no code implementations • 4 Jul 2018 • Tadanobu Inoue, Subhajit Chaudhury, Giovanni De Magistris, Sakyasingha Dasgupta
Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale image data.
no code implementations • 2 Jun 2018 • Daiki Kimura, Subhajit Chaudhury, Ryuki Tachibana, Sakyasingha Dasgupta
During reinforcement learning, the agent predicts the reward as a function of the difference between the actual state and the state predicted by the internal model.
no code implementations • 30 May 2018 • Fernando Camaro Nogues, Andrew Huie, Sakyasingha Dasgupta
In this work, we present an application of domain randomization and generative adversarial networks (GAN) to train a near real-time object detector for industrial electric parts, entirely in a simulated environment.
no code implementations • ICLR 2018 • Daiki Kimura, Subhajit Chaudhury, Ryuki Tachibana, Sakyasingha Dasgupta
We present a novel reward estimation method that is based on a finite sample of optimal state trajectories from expert demon- strations and can be used for guiding an agent to mimic the expert behavior.
no code implementations • 18 Dec 2017 • Farhan Shafiq, Takato Yamada, Antonio T. Vilchez, Sakyasingha Dasgupta
In this paper, we present an automatic flow from trained TensorFlow models to FPGA system on chip implementation of binarized CNN.
no code implementations • 17 Dec 2017 • Rudy Raymond, Takayuki Osogami, Sakyasingha Dasgupta
Gaussian DyBM is a DyBM that assumes the predicted data is generated by a Gaussian distribution whose first-order moment (mean) dynamically changes over time but its second-order moment (variance) is fixed.
no code implementations • 20 Sep 2017 • Tadanobu Inoue, Subhajit Chaudhury, Giovanni De Magistris, Sakyasingha Dasgupta
It detects object positions 6 to 7 times more precisely than the baseline of directly learning from the dataset of the real images.
no code implementations • 4 Jul 2017 • Subhajit Chaudhury, Sakyasingha Dasgupta, Asim Munawar, Md. A. Salam Khan, Ryuki Tachibana
We present a conditional generative model that maps low-dimensional embeddings of multiple modalities of data to a common latent space hence extracting semantic relationships between them.
no code implementations • 22 Sep 2016 • Sakyasingha Dasgupta, Takayuki Yoshizumi, Takayuki Osogami
We introduce Delay Pruning, a simple yet powerful technique to regularize dynamic Boltzmann machines (DyBM).
no code implementations • 11 Jun 2015 • Sakyasingha Dasgupta, Dennis Goldschmidt, Florentin Wörgötter, Poramate Manoonpong
The locomotive behaviors can consist of a variety of walking patterns along with adaptation that allow the animals to deal with changes in environmental conditions, like uneven terrains, gaps, obstacles etc.
no code implementations • 11 Jul 2014 • Guanjiao Ren, Weihai Chen, Sakyasingha Dasgupta, Christoph Kolodziejski, Florentin Wörgötter, Poramate Manoonpong
To address this problem, we extend the single chaotic CPG to multiple CPGs with learning.
no code implementations • 4 Feb 2014 • Sakyasingha Dasgupta
In this regard learning in neural networks can serve as a model for the acquisition of skills and knowledge in early development stages i. e. the ageing process and criticality in the network serves as the optimum state of cognitive abilities.