Advogato blog for sness

seewave - an R package for sound analysis and synthesis

Thu, 20 Jun 2013 02:17:24 GMT

seewave - an R package for sound analysis and synthesis:

'via Blog this'

Denoising Autoencoders (dA) — DeepLearning 0.1 documentation

Sat, 15 Jun 2013 01:16:12 GMT

Denoising Autoencoders (dA) — DeepLearning 0.1 documentation: "See section 4.6 of [Bengio09] for an overview of auto-encoders. An autoencoder takes an input and first maps it (with an encoder) to a hidden representation through a deterministic mapping, e.g.:"

'via Blog this'

Geoff Hinton - Recent Developments in Deep Learning - YouTube

Sat, 15 Jun 2013 01:16:12 GMT

Geoff Hinton - Recent Developments in Deep Learning - YouTube: ""

'via Blog this'

Naive Bayes classifier - Wikipedia, the free encyclopedia

Sat, 15 Jun 2013 01:16:12 GMT

Naive Bayes classifier - Wikipedia, the free encyclopedia: "In simple terms, a naive Bayes classifier assumes that the presence or absence of a particular feature is unrelated to the presence or absence of any other feature, given the class variable. For example, a fruit may be considered to be an apple if it is red, round, and about 3" in diameter. A naive Bayes classifier considers each of these features to contribute independently to the probability that this fruit is an apple, regardless of the presence or absence of the other features."

'via Blog this'

funny-white-unicorn-horn.jpg (450×368)

Fri, 14 Jun 2013 22:16:37 GMT

funny-white-unicorn-horn.jpg (450×368):

bextract - Google Search

Thu, 13 Jun 2013 22:16:33 GMT

bextract - Google Search: "If you find yourself using bextract, you probably have done something wrong"

'via Blog this'

How to Get Startup Ideas

Thu, 13 Jun 2013 18:16:27 GMT

How to Get Startup Ideas: "When a startup launches, there have to be at least some users who really need what they're making—not just people who could see themselves using it one day, but who want it urgently."

'via Blog this'

How to Get Startup Ideas

Thu, 13 Jun 2013 18:16:27 GMT

How to Get Startup Ideas: "Why do so many founders build things no one wants? Because they begin by trying to think of startup ideas. That m.o. is doubly dangerous: it doesn't merely yield few good ideas; it yields bad ideas that sound plausible enough to fool you into working on them."

'via Blog this'

Approximating Images With Random Lines - SickSad

Thu, 13 Jun 2013 17:16:43 GMT

Approximating Images With Random Lines - SickSad: "The algorithm works by randomly placing 40 black lines on 40 copies of a blank source image, each of those 40 is then compared to the goal image using SSIM to measure similarity. If any of the 40 are more similar than the source image that image is used as the source for the next iteration of the algorithm. If none of the 40 are more similar then the algorithm repeats with the original source image until a closer similarity is found."

'via Blog this'

Structural similarity - Wikipedia, the free encyclopedia

Thu, 13 Jun 2013 17:16:43 GMT

Structural similarity - Wikipedia, the free encyclopedia: "The structural similarity (SSIM) index is a method for measuring the similarity between two images. The SSIM index is a full reference metric; in other words, the measuring of image quality based on an initial uncompressed or distortion-free image as reference. SSIM is designed to improve on traditional methods like peak signal-to-noise ratio (PSNR) and mean squared error (MSE), which have proven to be inconsistent with human eye perception."

'via Blog this'