Class VBGMM

Variational Gaussian Mixture Model

Index

Constructors

Properties

_a0 _b0 _k _m _m0 _nu _nu0 _p _r _w _w0 _x

Accessors

covs effectivity means

Methods

_bernoulli _digamma fit init predict probability

Constructors

constructor

new VBGMM(a: number, b: number, k: number): VBGMM
Parameters
- a: number
  Tuning parameter
- b: number
  Tuning parameter
- k: number
  Initial number of clusters
Returns VBGMM
- Defined in lib/model/vbgmm.d.ts:10

Properties

_a0

_a0: number

_b0

_b0: number

_k

_k: number

_m

_m: Matrix<number>

_m0

_m0: Matrix<number>

_nu

_nu: Matrix<number>

_nu0

_nu0: number

_p

_p: Matrix<number>

_r

_r: any

_w

_w: any[]

_w0

_w0: Matrix<number>

_x

_x: Matrix<number[]>

Accessors

covs

get covs(): Matrix<number>[]
Covariances

Returns Matrix<number>[]
- Defined in lib/model/vbgmm.d.ts:23

effectivity

get effectivity(): boolean[]
Effectivity

Returns boolean[]
- Defined in lib/model/vbgmm.d.ts:28

means

get means(): Matrix
Means

Returns Matrix
- Defined in lib/model/vbgmm.d.ts:18

Methods

_bernoulli

_bernoulli(n: any): number
Parameters
- n: any
Returns number
- Defined in lib/model/vbgmm.d.ts:40

_digamma

_digamma(z: any): any
Parameters
- z: any
Returns any
- Defined in lib/model/vbgmm.d.ts:39

fit

fit(): void
Fit model.

Returns void
- Defined in lib/model/vbgmm.d.ts:44

init

init(datas: number[][]): void
Initialize model.
Parameters
- datas: number[][]
  Training data
Returns void
- Defined in lib/model/vbgmm.d.ts:33

predict

predict(data: number[][]): number[]
Returns predicted categories.
Parameters
- data: number[][]
  Sample data
Returns number[]
Predicted values
- Defined in lib/model/vbgmm.d.ts:60

probability

probability(data: number[][]): Matrix
Returns probability of the datas.
Parameters
- data: number[][]
  Sample data
Returns Matrix
Predicted values
- Defined in lib/model/vbgmm.d.ts:54