{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/ristretto-hardware-oriented-approximation-of","title":"Ristretto: Hardware-Oriented Approximation of Convolutional Neural Networks","arxiv_id":"1605.06402","date":"2016-05-20","proceeding":null,"authors":["Philipp Gysel"],"abstract":"Convolutional neural networks (CNN) have achieved major breakthroughs in\nrecent years. Their performance in computer vision have matched and in some\nareas even surpassed human capabilities. Deep neural networks can capture\ncomplex non-linear features; however this ability comes at the cost of high\ncomputational and memory requirements. State-of-art networks require billions\nof arithmetic operations and millions of parameters. To enable embedded devices\nsuch as smartphones, Google glasses and monitoring cameras with the astonishing\npower of deep learning, dedicated hardware accelerators can be used to decrease\nboth execution time and power consumption. In applications where fast\nconnection to the cloud is not guaranteed or where privacy is important,\ncomputation needs to be done locally. Many hardware accelerators for deep\nneural networks have been proposed recently. A first important step of\naccelerator design is hardware-oriented approximation of deep networks, which\nenables energy-efficient inference. We present Ristretto, a fast and automated\nframework for CNN approximation. Ristretto simulates the hardware arithmetic of\na custom hardware accelerator. The framework reduces the bit-width of network\nparameters and outputs of resource-intense layers, which reduces the chip area\nfor multiplication units significantly. Alternatively, Ristretto can remove the\nneed for multipliers altogether, resulting in an adder-only arithmetic. The\ntool fine-tunes trimmed networks to achieve high classification accuracy. Since\ntraining of deep neural networks can be time-consuming, Ristretto uses highly\noptimized routines which run on the GPU. This enables fast compression of any\ngiven network. Given a maximum tolerance of 1%, Ristretto can successfully\ncondense CaffeNet and SqueezeNet to 8-bit. The code for Ristretto is available.","url_abs":"http://arxiv.org/abs/1605.06402v1","url_pdf":"http://arxiv.org/pdf/1605.06402v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ristretto-hardware-oriented-approximation-of","repo_url":"https://github.com/DeepScale/SqueezeNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"ristretto-hardware-oriented-approximation-of","repo_url":"https://github.com/CEREBUSTER/effacinto","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":null,"task_name":"GPU"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"fire-module","method_name":"Fire Module"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"squeezenet","method_name":"SqueezeNet"},{"method_slug":"xavier-initialization","method_name":"Xavier Initialization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1605.06402","atlas_url":"https://app.syntology.ai/?focus=1605.06402","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1605.06402"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1605.06402\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1605.06402"},"call":"get_concepts_for_paper(arxiv_id=\"1605.06402\")"}],"by_repo":[{"repo":"DeepScale/SqueezeNet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"CEREBUSTER/effacinto","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"411f4eb4e99b9b8930db748d9e42ecf3794788fc948a967d348b93083d015d2c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}