Path: ...!eternal-september.org!feeder3.eternal-september.org!news.eternal-september.org!.POSTED!not-for-mail
From: Don Y <blockedofcourse@foo.invalid>
Newsgroups: comp.arch.embedded
Subject: =?UTF-8?Q?Re=3a_Neural_Networks_=28MNIST_inference=29_on_the_?=
 =?UTF-8?Q?=e2=80=9c3-cent=e2=80=9d_Microcontroller?=
Date: Mon, 21 Oct 2024 15:09:10 -0700
Organization: A noiseless patient Spider
Lines: 8
Message-ID: <vf6je9$145db$1@dont-email.me>
References: <GDBnsQalznyGTjeHEuVJnPScMPMUvCQe@news.usenet.farm>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Injection-Date: Tue, 22 Oct 2024 00:09:13 +0200 (CEST)
Injection-Info: dont-email.me; posting-host="d9590a746a261365d5190c213899d473";
	logging-data="1185195"; mail-complaints-to="abuse@eternal-september.org";	posting-account="U2FsdGVkX1//HKG7skLuYZirh+zUj/gg"
User-Agent: Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:102.0) Gecko/20100101
 Thunderbird/102.2.2
Cancel-Lock: sha1:jR3wPlqWtjtJmvz5NTddj355tAs=
In-Reply-To: <GDBnsQalznyGTjeHEuVJnPScMPMUvCQe@news.usenet.farm>
Content-Language: en-US
Bytes: 1452

On 10/21/2024 1:06 PM, D. Ray wrote:
> Is it possible to implement an MNIST inference engine, which can classify
> handwritten numbers, also on a PMS150C?

Wouldn't it be smarter to come up with an approach that *can*
rather than trying to force some approach to "fit"?