Dissertation · 2017 · Open access

Adapting deep neural networks to a low-power environment

Oscar Mañas Sánchez

RECERCAT (Consorci de Serveis Universitaris de Catalunya) · Published 1 January 2017

Open full textCite this paper

In brief

“Adapting deep neural networks to a low-power environment” is a 2017 dissertation by Oscar Mañas Sánchez, published in RECERCAT (Consorci de Serveis Universitaris de Catalunya). OpenAlex counts 0 citations as of 19 November 2026. It is open access: the full text is free to read at RECERCAT (Consorci de Serveis Universitaris de Catalunya).

Citations
0
Authors
1

Abstract

These days, working with deep neural networks goes hand in hand with the use of\nGPUs. Once a deep neural network has been trained for hours, days, or even weeks on\na desktop GPU, it is deployed in the field where it runs inference computations, which\nare far less expensive than training. This fact, in conjunction with the mobile nature of\ndeep learning applications, makes very interesting the possibility of running inference\nlocally on a mobile device.\nThere already exist mobile applications that can perform tasks involving deep neural\nnetworks, but they rely on remote servers to run the most expensive computations.\nThis is not ideal because the user’s privacy may be compromised or the algorithm\nperformance may be damaged due to latency issues on a poor network connection. In\nthis project, the possibility of running inference natively on a mobile GPU is explored.\nOne of the main applications of deep learning is object recognition, which encompasses\ndifferent problems such as classification, identification and detection. In this\nproject, we select a very deep neural network called Faster R-CNN, which solves a\ndetection problem, and optimize it to run natively on a mobile platform. This innovation\nprovides to a mobile device, such as a smartphone or a tablet, the capability of\nidentifying objects and its location in images, potentially improving the performance\nof applications that currently employ the device camera combined with deep neural\nnetworks.\nHowever, mobile devices have limitations in power, memory, and compute capability.\nThis makes power and memory hungry applications such as deep neural networks\nhard to deploy, requiring smart software design. As a result, mobile presents both an\nopportunity and challenge for machine learning systems.\nA preliminary profiling of the network on the Nvidia Jetson TX1 module, a stateof-the-art\nplatform used in modern smartphones and handheld consoles, shows that the\nconvolutional and fully-connected layers take most of the forward pass execution time,\nup to 88.16% of the total. The network parameters take 548.3 MBytes of space, an\n87.2% of which belong to fully-connected layers. Hence, the main performance and\nenergy bottlenecks are on the convolutional and fully-connected layers.\nIn order to overcome these bottlenecks, two optimizations are proposed. In first\nplace, we use half-precision floating points instead of single-precision; this reduces by\nhalf the memory bandwidth, improving performance and providing energy savings. In\nsecond place, we implement a neuron-pruning technique to remove up to 80% of the\nneurons in the fully-connected layers; pruning reduces the memory footprint of the\nnetwork model and the amount of FP operations, reducing both energy consumption\nand execution time.\nTo evaluate the aforementioned optimizations, thorough experimentation is carried\nout on a Nvidia Jetson TX1 module. Results show that, combining all the optimizations,\nwe obtain, on average, a speedup of 1.55x…

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Sánchez, O. M. (2017). Adapting deep neural networks to a low-power environment. RECERCAT (Consorci de Serveis Universitaris de Catalunya). http://hdl.handle.net/2117/106673

MLA 9

Sánchez, Oscar Mañas. “Adapting deep neural networks to a low-power environment.” RECERCAT (Consorci de Serveis Universitaris de Catalunya), 2017. http://hdl.handle.net/2117/106673.

Chicago

Sánchez, Oscar Mañas. 2017. “Adapting deep neural networks to a low-power environment.” RECERCAT (Consorci de Serveis Universitaris de Catalunya). http://hdl.handle.net/2117/106673.

Harvard

Sánchez, O. M. (2017) ‘Adapting deep neural networks to a low-power environment’, RECERCAT (Consorci de Serveis Universitaris de Catalunya). Available at: http://hdl.handle.net/2117/106673.

IEEE

O. M. Sánchez, “Adapting deep neural networks to a low-power environment,” RECERCAT (Consorci de Serveis Universitaris de Catalunya), 2017.

BibTeX

@phdthesis{sanchez2017adapting,
  title     = {{Adapting deep neural networks to a low-power environment}},
  author    = {Sánchez, Oscar Mañas},
  year      = {2017},
  url       = {http://hdl.handle.net/2117/106673}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • low-power inference
  • Faster R-CNN
  • object detection
  • mobile GPUs
  • half-precision floating-point
  • neuron pruning
  • fully connected layers
  • convolutional layers

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Sánchez, O. M. (2017). Adapting deep neural networks to a low-power environment. RECERCAT (Consorci de Serveis Universitaris de Catalunya). http://hdl.handle.net/2117/106673

How many times has this paper been cited?

0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at RECERCAT (Consorci de Serveis Universitaris de Catalunya): sign in and open the full text from this page.

Who wrote this paper?

Oscar Mañas Sánchez.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.