Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Michael Green: Deep probabilistic neural networks - A way forward

Michael Green: Deep probabilistic neural networks - A way forward

In a world where deep learning and other massively scalable perception machines are at our disposal, allowing us to build amazing applications, the time is now ripe to move beyond the concept of pure perception and into broader Artificial Intelligence (AI). The path towards AI goes through what's missing in many applications today; Inference. Only when we combine Inference machines and Perception machines can we truly talk about AI. The benefit will be a machine that knows what to expect before observing it's environment and that can take prior information into account. With ever more mature Probabilistic programming languages available, we can express this marriage of perception and inference. In this talk, we will scrape the surface of how to build Bayesian predictive inference machines using Probabilistic programming.

MunichDataGeeks

November 23, 2017
Tweet

More Decks by MunichDataGeeks

Other Decks in Technology

Transcript

  1. data { int<lower=0> N; vector[N] x; vector[N] y; } parameters

    { real alpha; real beta; real<lower=0> sigma; } model { real mu[N] = alpha + beta * x; y ~ normal(mu, sigma); } data { int<lower=0> N; vector[N] x; vector[N] y; } parameters { real alpha; real beta; real<lower=0> nu; real<lower=0> sigma; } model { real mu[N] = alpha + beta * x; y ~ student_t(nu, mu, sigma); }
  2. data { int<lower=0> N; vector[N] x; vector[N] y; } parameters

    { real alpha; real beta; real<lower=0> sigma; } model { real mu[N] = alpha + beta * x; y ~ normal(mu, sigma); } data { int<lower=0> N; vector[N] x; vector[N] y; } parameters { real alpha; real beta; real<lower=0> sigma; } model { vector[N] mu = exp(x*beta+alpha); y ~ neg_binomial_2(mu, sigma); }
  3. ## setting value ## version R version 3.4.2 (2017-09-28) ##

    system x86_64, linux-gnu ## ui X11 ## language en_US:en ## collate en_US.UTF-8 ## tz Europe/Copenhagen ## date 2017-11-23 ## ## package * version date source ## assertthat 0.1 2013-12-06 CRAN (R 3.4.2) ## backports 1.1.1 2017-09-25 CRAN (R 3.4.2) ## base * 3.4.2 2017-10-29 local ## bindr 0.1 2016-11-13 CRAN (R 3.4.2) ## bindrcpp * 0.2 2017-06-17 CRAN (R 3.4.2) ## bitops 1.0-6 2013-08-17 CRAN (R 3.4.2) ## caTools 1.17.1 2014-09-10 CRAN (R 3.4.2) ## colorspace 1.3-2 2016-12-14 CRAN (R 3.4.2) ## compiler 3.4.2 2017-10-29 local ## datasets * 3.4.2 2017-10-29 local ## devtools 1.13.4 2017-11-09 CRAN (R 3.4.2) ## digest 0.6.12 2017-01-27 CRAN (R 3.4.2) ## dplyr * 0.7.4 2017-09-28 CRAN (R 3.4.2) ## evaluate 0.10 2016-10-11 CRAN (R 3.4.2) ## gdata 2.18.0 2017-06-06 CRAN (R 3.4.2) ## ggplot2 * 2.2.1 2016-12-30 CRAN (R 3.4.2) ## glue 1.2.0 2017-10-29 CRAN (R 3.4.2) ## gplots * 3.0.1 2016-03-30 CRAN (R 3.4.2)