Zobrazeno 1 - 10
of 356
pro vyhledávání: '"JOHN, LIZY"'
Autor:
Nag, Shashank, Bacellar, Alan T. L., Susskind, Zachary, Jha, Anshul, Liberty, Logan, Sivakumar, Aishwarya, John, Eugene B., Kailas, Krishnan, Lima, Priscila M. V., Yadwadkar, Neeraja J., Franca, Felipe M. G., John, Lizy K.
Transformers are set to become ubiquitous with applications ranging from chatbots and educational assistants to visual recognition and remote sensing. However, their increasing computational and memory demands is resulting in growing energy consumpti
Externí odkaz:
http://arxiv.org/abs/2411.01818
Autor:
Bacellar, Alan T. L., Susskind, Zachary, Breternitz Jr., Mauricio, John, Eugene, John, Lizy K., Lima, Priscila M. V., França, Felipe M. G.
Publikováno v:
International Conference on Machine Learning (ICML) 2024
We introduce the Differentiable Weightless Neural Network (DWN), a model based on interconnected lookup tables. Training of DWNs is enabled by a novel Extended Finite Difference technique for approximate differentiation of binary values. We propose L
Externí odkaz:
http://arxiv.org/abs/2410.11112
Autor:
Abi-Karam, Stefan, Sarkar, Rishov, Seigler, Allison, Lowe, Sean, Wei, Zhigang, Chen, Hanqiu, Rao, Nanditha, John, Lizy, Arora, Aman, Hao, Cong
Machine learning (ML) techniques have been applied to high-level synthesis (HLS) flows for quality-of-result (QoR) prediction and design space exploration (DSE). Nevertheless, the scarcity of accessible high-quality HLS datasets and the complexity of
Externí odkaz:
http://arxiv.org/abs/2405.00820
Bit-serial Processing-In-Memory (PIM) is an attractive paradigm for accelerator architectures, for parallel workloads such as Deep Learning (DL), because of its capability to achieve massive data parallelism at a low area overhead and provide orders-
Externí odkaz:
http://arxiv.org/abs/2311.11384
Autor:
Susskind, Zachary, Arora, Aman, Miranda, Igor D. S., Bacellar, Alan T. L., Villon, Luis A. Q., Katopodis, Rafael F., de Araujo, Leandro S., Dutra, Diego L. C., Lima, Priscila M. V., Franca, Felipe M. G., Breternitz Jr., Mauricio, John, Lizy K.
The deployment of AI models on low-power, real-time edge devices requires accelerators for which energy, latency, and area are all first-order concerns. There are many approaches to enabling deep neural networks (DNNs) in this domain, including pruni
Externí odkaz:
http://arxiv.org/abs/2304.10618
Machine Learning (ML) has been widely adopted in design exploration using high level synthesis (HLS) to give a better and faster performance, and resource and power estimation at very early stages for FPGA-based design. To perform prediction accurate
Externí odkaz:
http://arxiv.org/abs/2302.10977
Autor:
Arora, Aman, Anand, Tanmay, Borda, Aatman, Sehgal, Rishabh, Hanindhito, Bagus, Kulkarni, Jaydeep, John, Lizy K.
Block RAMs (BRAMs) are the storage houses of FPGAs, providing extensive on-chip memory bandwidth to the compute units implemented using Logic Blocks (LBs) and Digital Signal Processing (DSP) slices. We propose modifying BRAMs to convert them to CoMeF
Externí odkaz:
http://arxiv.org/abs/2203.12521
Autor:
Susskind, Zachary, Arora, Aman, Miranda, Igor Dantas Dos Santos, Villon, Luis Armando Quintanilla, Katopodis, Rafael Fontella, de Araujo, Leandro Santiago, Dutra, Diego Leonel Cadette, Lima, Priscila Machado Vieira, Franca, Felipe Maia Galvao, Breternitz Jr., Mauricio, John, Lizy K.
Weightless Neural Networks (WNNs) are a class of machine learning model which use table lookups to perform inference. This is in contrast with Deep Neural Networks (DNNs), which use multiply-accumulate operations. State-of-the-art WNN architectures h
Externí odkaz:
http://arxiv.org/abs/2203.01479