Experimental browser for the Atmosphere
How can we design neural networks that take neural network parameters as input? This fundamental question arises in applications as diverse as generating neural network weights, processing implicit neural representations, and predicting generalization performance. [2/9]
Mar 21, 2024, 6:35 PM
{
"text": "How can we design neural networks that take neural network parameters as input?\nThis fundamental question arises in applications as diverse as generating neural network weights, processing implicit neural representations, and predicting generalization performance.\n[2/9]",
"$type": "app.bsky.feed.post",
"reply": {
"root": {
"cid": "bafyreib5dtyi4z6vjnwkzr7whcg5miwringoqamytsasjkcl3ch2gjucr4",
"uri": "at://did:plc:7eq6i3fyeqin2cyf6b5xibaj/app.bsky.feed.post/3lhletoodox2d"
},
"parent": {
"cid": "bafyreib5dtyi4z6vjnwkzr7whcg5miwringoqamytsasjkcl3ch2gjucr4",
"uri": "at://did:plc:7eq6i3fyeqin2cyf6b5xibaj/app.bsky.feed.post/3lhletoodox2d"
}
},
"createdAt": "2024-03-21T18:35:40.000Z"
}