Spaces:
Running
Running
File size: 3,978 Bytes
c964813 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 | {
"algorithms": [
{
"id": "gradient_descent",
"label": "Gradient descent",
"params": [
{ "name": "learning_rate", "label": "Learning rate η", "symbol": "η", "kind": "number", "min": 0, "minExclusive": true, "default": 0.1, "description": "How far each step moves along the negative gradient." },
{ "name": "momentum", "label": "Momentum μ", "symbol": "μ", "kind": "number", "min": 0, "max": 1, "maxExclusive": true, "default": 0.0, "description": "How much of the previous step carries over into the next one." }
]
},
{
"id": "nesterov",
"label": "Nesterov momentum",
"params": [
{ "name": "learning_rate", "label": "Learning rate η", "symbol": "η", "kind": "number", "min": 0, "minExclusive": true, "default": 0.1, "description": "How far each step moves along the negative gradient." },
{ "name": "momentum", "label": "Momentum μ", "symbol": "μ", "kind": "number", "min": 0, "max": 1, "maxExclusive": true, "default": 0.1, "description": "How much of the previous step carries over; the gradient is taken at the look-ahead point." }
]
},
{
"id": "newton",
"label": "Newton's method",
"params": []
},
{
"id": "adam",
"label": "Adam",
"params": [
{ "name": "learning_rate", "label": "Learning rate η", "symbol": "η", "kind": "number", "min": 0, "minExclusive": true, "default": 0.1, "description": "The largest step size, roughly." },
{ "name": "beta1", "label": "Decay β₁", "symbol": "β₁", "kind": "number", "min": 0, "max": 1, "maxExclusive": true, "default": 0.9, "description": "Decay rate of the moving average of gradients (first moment)." },
{ "name": "beta2", "label": "Decay β₂", "symbol": "β₂", "kind": "number", "min": 0, "max": 1, "maxExclusive": true, "default": 0.999, "description": "Decay rate of the moving average of squared gradients (second moment)." },
{ "name": "epsilon", "label": "Epsilon ε", "symbol": "ε", "kind": "number", "min": 0, "minExclusive": true, "default": 1e-8, "description": "Added to the denominator to avoid dividing by zero." }
]
},
{
"id": "adagrad",
"label": "Adagrad",
"params": [
{ "name": "learning_rate", "label": "Learning rate η", "symbol": "η", "kind": "number", "min": 0, "minExclusive": true, "default": 0.1, "description": "Divided by the root of the summed squared gradients." },
{ "name": "epsilon", "label": "Epsilon ε", "symbol": "ε", "kind": "number", "min": 0, "minExclusive": true, "default": 1e-8, "description": "Added to the denominator to avoid dividing by zero." }
]
},
{
"id": "rmsprop",
"label": "RMSProp",
"params": [
{ "name": "learning_rate", "label": "Learning rate η", "symbol": "η", "kind": "number", "min": 0, "minExclusive": true, "default": 0.1, "description": "Divided by the root of the moving average of squared gradients." },
{ "name": "beta", "label": "Decay β", "symbol": "β", "kind": "number", "min": 0, "max": 1, "maxExclusive": true, "default": 0.9, "description": "Decay rate of the moving average of squared gradients." },
{ "name": "epsilon", "label": "Epsilon ε", "symbol": "ε", "kind": "number", "min": 0, "minExclusive": true, "default": 1e-8, "description": "Added to the denominator to avoid dividing by zero." }
]
},
{
"id": "adadelta",
"label": "Adadelta",
"params": [
{ "name": "beta", "label": "Decay β", "symbol": "β", "kind": "number", "min": 0, "max": 1, "maxExclusive": true, "default": 0.9, "description": "Decay rate of the moving averages of squared gradients and squared updates." },
{ "name": "epsilon", "label": "Epsilon ε", "symbol": "ε", "kind": "number", "min": 0, "minExclusive": true, "default": 0.001, "description": "Sets the first step size, and avoids dividing by zero." }
]
}
]
}
|