Tech papers
Get flash to fully experience Pearltrees
The cerebral cortex is a remarkable computational system [DM07] . It uses slow, unreliable and inhomogeneous computing elements, and yet it outperforms the most powerful computers in relatively routine functions such as, for example, vision. The disparity between the effectiveness of computation in cortical circuits systems and in a computer, in such types of functions, is primarily attributable to the way the elementary devices are used in the system, and to the kind of computational primitives they implement [M90] . Rather than using Boolean logic, precise digital representations, and clocked operations, cortical circuits carry out robust and reliable computation using hybrid analog/digital components; they emphasize distributed, event-driven, collective, and massively parallel mechanisms, and make extensive use of adaptation, self-organization and learning.
soft Winner-Take-All networks as models of cortical computation — Neuromorphic Cognitive Systems
Hasegawa Lab., Tokyo Institute of Technology
Furao Shen and Osamu Hasegawa, "Self-organizing Incremental Neural Network and its Applications", Tutorial, International Joint Conference on Neural Networks (IJCNN 2009) [ slide ] Abstract What is SOINN?
自己増殖型ニューラルネットワーク（SOINN）は，Growing Neural Gas（GNG）と自己組織化マップ (SOM) を拡張した，追加学習可能なオンライン教師なし学習手法です．具体的には，非定常（動的に形状が変化する）で，かつ複雑な形状を持つ分布からオンラインで得られる入力に対して，ネットワークを自己組織的に形成し，適切なクラス数と入力分布の位相構造を出力することができます．また，事前にネットワークの構造を決定する必要がないほか，高いノイズ耐性を有し，計算が軽いなどの特長があります．そのため，SOINNは特に実世界のデータ処理に有効であり，画像や音声などのパターンの学習・認識や，実環境でオンライン・リアルタイムに稼働する知能ロボットなどに効果的に活用できます． Furao Shen and Osamu Hasegawa, "Self-organizing Incremental Neural Network and its Applications", Tutorial, International Joint Conference on Neural Networks (IJCNN 2009) [ スライド資料 ] Abstract What is SOINN?
東京工業大学 長谷川研究室 (Hasegawa Lab.)
HTM algorithms - numenta.com
This page describes an overview of the HTM cortical learning algorithms. For a detailed description of the algorithms, see our paper on HTM cortical learning algorithms available in the papers section of the web site. HTM networks are modeled on the neocortex, the seat of human intelligence. They capture the essence of how humans learn, recognize patterns, and make predictions.
Frontiers | A cortical sparse distributed coding model linking mini- and macrocolumn-scale functionality | Frontiers in Neuroanatomy
Introduction The columnar organization of neocortex at the minicolumnar (20–50 μm) and macrocolumnar (300–600 μm) scales has long been known (see Mountcastle, 1997 ; Horton and Adams, 2005 for reviews). Minicolumn-scale organization has been demonstrated on several anatomical bases ( Lorente de No, 1938 ; DeFelipe et al., 1990 ; Peters and Sethares, 1996 ). There has been substantial debate as to whether this highly regular minicolumn-scale structure has some accompanying generic dynamics or functionality.In deriving a gradient-based update rule for recurrent networks, we now make network connectivity very very unconstrained. We simply suppose that we have a set of input units, I = { x k (t), 0 Let W be the weight matrix with n rows and n+m columns, where w i,j is the weight to unit i (which is in U ) from unit j (which is in I or U ).
Real Time Recurrent Learning
A Tonotopic Artificial Neural Network Architecture
Nikko Ström (1997): " A Tonotopic Artificial Neural Network Architechture for Phoneme Probability Estimation, " Proc. of the 1997 IEEE Workshop on Speech Recognition and Understanding , pp. 156-163, Santa Barbara, CA. Abstract - A novel sparse ANN connection scheme is proposed. It is inspired by the so called tonotopic organization of the auditory nerve, and allows a more detailed representation of the speech spectrum to be input to an ANN than is commonly used. A consequence of the new connection scheme is that more resources are allocated to analysis within narrow frequency sub-bands - a concept that has recently been investigated by others with so called sub-band ASR. ANNs with the proposed architecture have been evaluated on the TIMIT database for phoneme recognition, and are found to give better phoneme recognition performance than ANNs based on standard mel frequency cepstrum input.
Radial basis function (RBF) neural networks offer an efficient mechanism for approximating complex nonlinear functions [ 1 ], pattern recognition [ 2 ], modeling and controlling dynamic systems [ 3 , 4 ] from the input–output data. In fact, the selection of RBF neural network for a special application is dependent on its structure and learning abilities. Recently, with the research objects becoming more and more complex, the conventional RBF neural network with the fixed structures can not satisfy the requirement. The most difficult bottlenecks are the initial number of the hidden nodes, the initial position, and width of the RBF nodes. In order to solve the previously mentioned problems, some colleagues have found several kinds of methods.
