DR.GEEK
Dec 30, 20201 min read
Entropy In this time, we are considering entropy for following cases.
(30th-December-2020) Information Gain are followings. • How much entropy can be reduced when dividing a set of cases focusing on certain...
top of page
Search
DR.GEEK
Dec 29, 20201 min read
Learning data example
(29th-December-2020) Which attribute to split? We want to make a small decision tree As a result of division, divide the learning data...
DR.GEEK
Dec 28, 20201 min read
Disjunction of conjunctions
(28th-December-2020) Decision Trees question Discrete attribute values Target is also discrete Disjunctive description is required An...
DR.GEEK
Dec 28, 20201 min read
Learning of Decision Trees
(27th-December-2020) 決定木（Decision Trees） are following factors. Disjunction of conjunctions Practical classifier Diagnosis of disease...
DR.GEEK
Dec 28, 20201 min read
Real time observation of trading bots
(26th-December-2020) • For real time observation of trading bots, make a guess assumption for real trading data. • For example, from last...
DR.GEEK
Dec 28, 20201 min read
DATA mining for AI trading markers& New approach of Arbitrage bots
(25th-December-2020) • For AI trading bots development, we should design highest accuracy markers and its formula. We select multiple...
DR.GEEK
Dec 24, 20202 min read
Other Generation Schemes
(24th-December-2020) • The methods we have described so far use either MCMC sampling, ancestral sampling, or some mixture of the two to...
DR.GEEK
Dec 23, 20202 min read
Walk-Back Training Procedure
(23th-December-2020) • The walk-back training procedure was proposed by ( ) as a way Bengio et al. 2013c to accelerate the convergence of...
DR.GEEK
Dec 22, 20201 min read
Clamping and Conditional Sampling
(22th-December-2020) • Similarly to Boltzmann machines, denoisingautoencoders and their generalizations (such as GSNs, described below)...
DR.GEEK
Dec 21, 20201 min read
Drawing Samples from Autoencoders
(21th-December-2020) • we saw that many kinds of autoencoders learn the data distribution. 14 There are close connections between score...
DR.GEEK
Dec 20, 20201 min read
NADE
(20th-December-2020) • The neural autoregressive density estimator (NADE) is a very successful recent form of neural auto-regressive...
DR.GEEK
Dec 19, 20202 min read
Neural Auto-Regressive Networks
(19th-December-2020) • Neural auto-regressive networks ( , , ) have the same Bengio and Bengio 2000a b left-to-right graphical model as...
DR.GEEK
Dec 18, 20201 min read
Linear Auto-Regressive Networks
(18th-December-2020) • The simplest form of auto-regressive network has no hidden units and no sharing of parameters or features. Each...
DR.GEEK
Dec 17, 20201 min read
Auto-Regressive Networks
(17th-December-2020) • Auto-regressive networks are directed probabilistic models with no latent random variables. The conditional...
DR.GEEK
Dec 16, 20201 min read
Generative Moment Matching Networks
(16th-December-2020) • Generative moment matching networks( , ; , Li et al. 2015 Dziugaite et al. 2015) are another form of generative...
DR.GEEK
Dec 15, 20201 min read
Generative Adversarial Networks
(15th-December-2020) • Generative adversarial networks or GANs ( , ) are another Good fellow et al. 2014c generative modeling approach...
DR.GEEK
Dec 14, 20202 min read
Differentiable Generator Nets
(14th-December-2020) • Many generative models are based on the idea of using a differentiable generator network. The model transforms...
DR.GEEK
Dec 13, 20201 min read
Directed Generative Nets
(13th-December-2020) • As discussed in chapter , directed graphical models make up a prominent class 16 of graphical models. While...
DR.GEEK
Dec 12, 20201 min read
Back-Propagating through Discrete Stochastic Operations
(12th-December-2020) When a model emits a discrete variable y, the reparametrization trick is not applicable. Suppose that the model...
DR.GEEK
Dec 11, 20201 min read
Back-Propagation through Random Operations
(11th-December-2020) Traditional neural networks implement a deterministic transformation of some input variables x. When developing...
bottom of page