In this issue of ′ Pteridologist’ (pdf warning), there are two short communications (pp. 12-15) on the difficulties of identifying British species of Dryopteris (male ferns) and Polypodium, with a note on the inconstancy of morphological features of plants in the field. (I mean, okay, some species hybridize, but what the heck does it mean when a probably hybride plant has a frond or two looking just like one of the parents? somatical mutations?..)
‘Pteridologist’ as a whole is a ‘nice’ magazine—easy language, cultural/biogeographical/anatomical forkfuls, lots of photoes. Enjoy!
“This paper is a review of the evolutionary history of deep learning models. It covers from the genesis of neural networks when associationism modeling of the brain is studied, to the models that dominate the last decade of research in deep learning like convolutional neural networks, deep belief networks, and recurrent neural networks, and extends to popular recent models like variational autoencoder and generative adversarial nets.”
Deep Forest: Towards An Alternative to Deep Neural Networks
“The training process of gcForest is efficient and scalable. In our experiments its training time running on a PC is comparable to that of deep neural networks running with GPU facilities, and the efficiency advantage may be more apparent because gcForest is naturally apt to parallel implementation. Furthermore, in contrast to deep neural networks which require large-scale training data, gcForest can work well even when there are only small-scale training data. Moreover, as a tree-based approach, gcForest should be easier for theoretical analysis than deep neural networks.”
Website of an experimental camera made with 32.000 drinking straws and photosensitive paper. Gives a 1:1 picture of what it “sees”, little depth of picture; I keep thinking that it ought to be used for research in some way, but so far haven’t an exact idea.
Short Online Texts Thread
In this issue of ′ Pteridologist’ (pdf warning), there are two short communications (pp. 12-15) on the difficulties of identifying British species of Dryopteris (male ferns) and Polypodium, with a note on the inconstancy of morphological features of plants in the field. (I mean, okay, some species hybridize, but what the heck does it mean when a probably hybride plant has a frond or two looking just like one of the parents? somatical mutations?..)
‘Pteridologist’ as a whole is a ‘nice’ magazine—easy language, cultural/biogeographical/anatomical forkfuls, lots of photoes. Enjoy!
Singing above the chorus: cooperative Princess cichlid fish (Neolamprologus pulcher) has high pitch—teleost fishes communicate; they might use sound for it; proving it is difficult, because it’s difficult to study their hearing.
On the Origin of Deep Learning
https://arxiv.org/abs/1702.07800
“This paper is a review of the evolutionary history of deep learning models. It covers from the genesis of neural networks when associationism modeling of the brain is studied, to the models that dominate the last decade of research in deep learning like convolutional neural networks, deep belief networks, and recurrent neural networks, and extends to popular recent models like variational autoencoder and generative adversarial nets.”
Deep Forest: Towards An Alternative to Deep Neural Networks
https://arxiv.org/abs/1702.08835#
“The training process of gcForest is efficient and scalable. In our experiments its training time running on a PC is comparable to that of deep neural networks running with GPU facilities, and the efficiency advantage may be more apparent because gcForest is naturally apt to parallel implementation. Furthermore, in contrast to deep neural networks which require large-scale training data, gcForest can work well even when there are only small-scale training data. Moreover, as a tree-based approach, gcForest should be easier for theoretical analysis than deep neural networks.”
Website of an experimental camera made with 32.000 drinking straws and photosensitive paper. Gives a 1:1 picture of what it “sees”, little depth of picture; I keep thinking that it ought to be used for research in some way, but so far haven’t an exact idea.