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