Working notes from the Scandinavian Institute for Computational Vandalism

Tag Archives: classification

The ‘dawning’ of an aspect

“I contemplate a face, and then suddenly notice its likeness to another. I see that it has not changed; and yet I see it differently. I call this experience “noticing an aspect…” And I must distinguish between the ‘continuous seeing’ of an aspect and the ‘dawning’ of an aspect… I see two pictures, with the […]

The cloudy days of machine learning

Once upon a time, the US Army wanted to use neural networks to automatically detect camouflaged enemy tanks. The researchers trained a neural net on 50 photos of camouflaged tanks in trees, and 50 photos of trees without tanks. Using standard techniques for supervised learning, the researchers trained the neural network to a weighting that […]

Convolutional Network, 1993

In 1988, Yann LeCun joined the Adaptive Systems Research Department at AT&T Bell Laboratories in Holmdel, New Jersey, United States, headed by Lawrence D. Jackel, where he developed a number of new machine learning methods, such as a biologically inspired model of image recognition called Convolutional Neural Networks, the “Optimal Brain Damage” regularization methods, and […]

Comparative Ways of Seeing

Your browser does not support the video tag. In the frame of Ways of Machine Seeing, a series of experiments in collaboration wit Geoff Cox on the the four episodes of the BBC documentary series Ways of Seeing. In this probe, the same algorithm runs an object detection script using two different training sets. For […]

You were asked to draw an angel

Playing with Quickdraw

In the cage

It had occurred to her early that in her position–that of a young person spending, in framed and wired confinement, the life of a guinea-pig or a magpie–she should know a great many persons without their recognising the acquaintance. That made it an emotion the more lively–though singularly rare and always, even then, with opportunity […]


Binford, O.T. & Nevatia, R (1977) Description and Recognition of Curved Objects, Artificial Intelligence 8(1):77-98.

Native contours

In this experiment [Hochberg & Brooks, 1962], a human baby was raised until the age of 19 months under the constant supervision of his parents who avoided exposing the child to line-drawings or two-dimensional pictures of any kind. Although the baby accidentally had opportunities to glance at some pictures on a few occasions, at no […]

Regression = prediction

[…] these sorts of problems break down into two types: regression problems, in which you need to predict some number, such as weight, given a bunch of other numbers, such as height; and classification problems, in which you need to assign a label, such as spam, given a bunch of numbers, for examples word counts […]

Green Mamba

Tensorflow, an open source library for Machine Learning developed by Google, comes with a demo program that labels images. The output of the program contains the labels (or class names) and their scores. The score represents the probability of the image to belong to a certain class. green mamba (score = 0.43074) vine snake (score […]