By utilizing a new deenition of product, we develop a neural net model. The memorization and generalization capabilities are investigated in an Information Theory fashion. To show the memorization capabilities, we use it as a decoder, and prove the net reduces the error probability to zero in the range of the error correcting capacity of the used code. To show the generalization capabilities, w...

Multi-layer feedforward neural networks are trained using the error back-propagation(BP) algorithm. This algorithm minimizes the error between outputs of a neural network(NN) and training data. Hence, in the case of noisy training data, a trained network memorizes noisy outputs for given inputs. Such learning is called rote memorization learning(RML). In this paper we propose error correcting m...

It is essential that students develop fluency in basic multiplication during grades three through five, in order to achieve mastery of elementary arithmetic. Instruction during these grades is typically focused on teaching students multiplication facts via drills and rote memorization so they are able to quickly retrieve answers to multiplication facts. If automaticity of multiplication facts i...

The ability of animals to visually memorize and categorize a large number of pictures is well established. Determining the kinds of information animals use to accomplish these goals has been more difficult. This experiment examined the contribution of spatial frequency information to picture memorization by pigeons. A series of grayscale pictures were notch-filtered to eliminate different porti...

Large deep neural networks are powerful, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup, a simple learning principle to alleviate these issues. In essence, mixup trains a neural network on convex combinations of pairs of examples and their labels. By doing so, mixup regularizes the neural network to favor simple lin...

It has been proposed that human category learning consists of an early abstraction-based stage followed by a later exemplar-memorization stage. To investigate whether similar processing stages extend to category learning in a nonverbal species, we applied a prototype-exception paradigm to investigating pigeon category learning. Five birds and 8 humans learned six-dimensional perceptual categori...

The stroke sequence of kanji has been investigated chiefly from the viewpoint of energy in the dynamics of writing together with the informational viewpoint in memorization in learning. Sample characters include all the members for daily use, and also katakana. The results show that the standard sequence fundamentally follows the law of energy minimization in writing movements, The degree of sa...