Experimental browser for the Atmosphere
Loading post...
{ "uri": "at://did:plc:fbkipu3c5tczzv7qack542zo/app.bsky.feed.like/3ld5ojaurjd27", "cid": "bafyreif6z2bgsh4c5opctyfkkbjftwwuberfpdabcz6l4wlvdib3dgj4py", "value": { "$type": "app.bsky.feed.like", "subject": { "cid": "bafyreifrqsimo65vmjoqmvafhzlkryu6wa4g7czopj4qrmbsq652ynusrq", "uri": "at://did:plc:3pzeixihe6cmldmipcqd2bjy/app.bsky.feed.post/3ld2lw73noz24" }, "createdAt": "2024-12-13T01:55:01.451Z" } }
How do a neural network's final parameters depend on its initial ones? In this new paper, we answer this question by analyzing the training Jacobian, the matrix of derivatives of the final parameters with respect to the initial parameters. https://arxiv.org/abs/2412.07003
Dec 11, 2024, 8:30 PM