Synaptic Dynamics: Unsupervised Learning Part I Xiao Bing 三D
Synaptic Dynamics: Unsupervised Learning Part Ⅰ Xiao Bing
Input Output 处理 单元 Input Output 处理 单元
处理 单元 处理 单元 Input Input Output Output
outline 。Learning Supervised Learning and Unsupervised Learning Supervised Learning and Unsupervised Learning in neural network Four Unsupervised Learning Laws
outline • Learning • Supervised Learning and Unsupervised Learning • Supervised Learning and Unsupervised Learning in neural network • Four Unsupervised Learning Laws
outline ·Learning Supervised Learning and Unsupervised Learning Supervised Learning and Unsupervised Learning in neural network Four Unsupervised Learning Laws
outline • Learning • Supervised Learning and Unsupervised Learning • Supervised Learning and Unsupervised Learning in neural network • Four Unsupervised Learning Laws
Learning Encoding A system learns a pattern if the system encodes the pattern in its structure. Change 。 A system learns or adapts or“self-organizes” when sample data changes system parameters. ·Quantization A system learns only a small proportion of all patterns in the sampled pattern environment,so quantization is necessary
Learning • Encoding A system learns a pattern if the system encodes the pattern in its structure. • Change A system learns or adapts or “self -organizes” when sample data changes system parameters. • Quantization A system learns only a small proportion of all patterns in the sampled pattern environment, so quantization is necessary
Learning II 。Encoding: A system learns a pattern if the system encodes the pattern in its structure. 。 Change: A system learns or adapts or "self -organizes"when sample data changes system paramefers. Quantization A system learns only a small proportion of all patterns in the sampled environment
Learning • Encoding: A system learns a pattern if the system encodes the pattern in its structure. • Change: A system learns or adapts or “self -organizes” when sample data changes system parameters. • Quantization A system learns only a small proportion of all patterns in the sampled pattern environment
Encoding A system has Learned a stimulus- response)pair y五 ·If(xy,) is a sample from the functjor"-R A system has learnedf if the system responses withy for x y=f(x) ,and
Encoding • A system has Learned a stimulusresponse pair ( , ) i i x y S xi yi • If is a sample from the function A system has learned if the system responses with for all ,and . n p ( , ) x y i i f : R → R f y x y = f (x)
Encoding Close to X Close to y,y=f(x A system has partially learned or approximated the function
Encoding x ′ y ′ x S Close to Close to , y • A system has partially learned or approximated the function . f y = f (x)
Learning Encoding: A system learns a pattern if the system encodes the pattern in its structure. ·Change: A system learns or adapts or "self organizes"when sample data changes system parameters. Quantization A system learns only a small proportion of all patterns in the sampled pattern environment
Learning • Encoding: A system learns a pattern if the system encodes the pattern in its structure. • Change: A system learns or adapts or “self - organizes” when sample data changes system parameters. • Quantization A system learns only a small proportion of all patterns in the sampled pattern environment
Change 。·We have learned calculus if our calculus- exam-behavior has changed from failing to passing. A system learns when pattern stimulation change a memory medium and leaves it changed for some comparatively long stretch of time
Change • We have learned calculus if our calculusexam-behavior has changed from failing to passing. • A system learns when pattern stimulation change a memory medium and leaves it changed for some comparatively long stretch of time