Getting an accuracy prediction for our own dataset

[bakigkgz1]

Hello. Can we run our own datasets on this system? For example, can we load the MNIST dataset into this system and get an accuracy prediction? Thank you very much in advance for your interest.

[alex-nugent]

Memristor Discovery V2 uses a chip with 16 discrete memristors to create a tiny neuron with 8 differential pair synapses. No, you cannot use that for accurate classification of MNIST.

[timmolter]

We did however do a more basic classify experiment, which you can read about here: https://github.com/knowm/memristor-discovery/blob/develop/src/main/resources/help/Classify12.md Also we have a video on it: https://vimeo.com/254209959.

[bakigkgz1]

Dear Professor, hello. First of all, thank you very much for taking the time to answer my question. I watch your videos and I am also subscribed to your YouTube channel. As far as I understand, we cannot upload our own dataset and perform prediction tasks. However, in one of your videos, you imported a file with a DIMACS extension and conducted a trial with it, so I was wondering if we could work with different datasets for that. Thank you again, and I wish you good work. Tim Molter ***@***.***>, 16 May 2024 Per, 21:32 tarihinde şunu yazdı:

…

We did however do a more basic classify experiment, which you can read about here: https://github.com/knowm/memristor-discovery/blob/develop/src/main/resources/help/Classify12.md Also we have a video on it: https://vimeo.com/254209959. — Reply to this email directly, view it on GitHub <#78 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AI6Q7AUCLGFSJPDL3ZZSBL3ZCT3U7AVCNFSM6AAAAABH2S426CVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDCMJVHE2DANBTGE> . You are receiving this because you authored the thread.Message ID: ***@***.***>

-- Ögr.Gör.Baki GÖKGÖZ Gümüşhane Üniversitesi www.bakigokgoz.com ***@***.***