神經(jīng)網(wǎng)絡的邏輯分析
LOGICAL ANALYSIS FOR NEURAL NETWORKS
-
摘要: 本文對比約束滿足網(wǎng)絡,描述了連續(xù)狀態(tài)神經(jīng)網(wǎng)絡的邏輯理論的基本框架,給出了矛盾的定量分析方法。分析表明,神經(jīng)元邏輯狀態(tài)變化的根本原因是網(wǎng)絡中存在優(yōu)勢矛盾;神經(jīng)網(wǎng)絡求解的動態(tài)過程對應于消除優(yōu)勢矛盾的過程。
-
關(guān)鍵詞:
- 神經(jīng)網(wǎng)絡; 約束滿足網(wǎng)絡; 推理; 矛盾分析
Abstract: By comparison with constraint satisfaction networks, this paper presents an essential frame of the logical theory for continuous-state neural networks, and gives the quantitative analyzing method for contradiction. The analysis indicates that the basic reason for the alternation of the logical states of the neurons is the existence of superior contradiction inside the networks. The dynamic process for a neural network to find a solution corresponds to eliminating the superior contradiction. -
Montanari U, Rossi F. Constraint relaxation may be perfect[J].Artificial Intelligence.1991, 48(2):143-170[2]Touretzky D S, Hinton G E. A distributed connectionist production system[J].Cognitive Science.1988, 12(3):423-466[3]Guesgen H W, Hertzberg J. A constraint-based approach to sptiotemporal reasoning. Applied Intel-[4]ligence, 1991,3(1): 71-90.[5]Hopfield J J. Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Natl. Acad. Sci. USA, 1984, 3088-3092.[6]Sejnowski T J, Kienker P K, Hinton G E. Learning symmetry groups with hidden units: Beyond the perceptron. Physica, 1988, 22D: 260-275.[7]Grossberg S, Mingolla E, Todorovic D. A neural network architecture for preattentive vision. IEEE Trans. on BME, 1989, BME-36(1): 65-84. -
計量
- 文章訪問數(shù): 1842
- HTML全文瀏覽量: 91
- PDF下載量: 384
- 被引次數(shù): 0
下載:
