Survey
* Your assessment is very important for improving the work of artificial intelligence, which forms the content of this project
* Your assessment is very important for improving the work of artificial intelligence, which forms the content of this project
PSY105 Neural Networks 2/5 2. “A universe of numbers” Lecture 1 recap • We can describe patterns at one level of description that emerge due to rules followed at a lower level of description. • Neural network modellers hope that we can understand behaviour by creating models of networks of artificial neurons. Warren McCullock 1943 - First artificial neuron model Warren McCulloch (neurophysiologist) Walter Pitts (mathematician) A simple artificial neuron Threshold logic unit (TLU) input weight activation Add Threshold Multiply inputs by weights and add. If the sum is larger than a threshold output 1, otherwise output 0 TLU: the output relation output 1 activation 0 threshold The relation is non-linear – small changes in activation give different changes in the output depending on the initial activation Model neuron function, reminders… • Inputs vary, they can be 0 or 1 – Weights change, effectively ‘interpreting’ inputs • There is a weight for each input – This can be a +ve number (excitation) or a –ve number (inhibition) – Weights do not change when inputs change • Activation = weighted sum of inputs – Activation = input1 x weight1 + input2xweight2 etc • If activation>threshold, output = 1, otherwise output=0 – Threshold = 1 States, weights & functions • States: all the possible combinations of inputs • Weights: how each input is multiplied before contributing to the activation of the unit • Functions: a way inputs are combined to produce outputs Computing with neurons: identify (1) input output weight X Input State 1 State 2 • 0 • 1 Weight • 0.7 • 0.7 Act. Activation • 0 • 0.7 Threshold = 1 ? Output • 0 • 0 Computing with neurons: identity (2) input output weight Act. Input State 1 State 2 • 0 • 1 Weight • 1 • 1 Activation • 0 • 1 Threshold = 1 ? Output • 0 • 1 Question: How could you use these simple neurons (TLUs) to compute the AND function? Input 1 •0 •0 •1 •1 Input 2 •0 •1 •0 •1 Output •0 •1 •1 •1 Computing with neurons: AND inputs output weights Act. Input 1 State 1 State 2 State 3 State 4 •0 •0 •1 •1 Threshold = 1, Input 2 •0 •1 •0 •1 Activation •0 • 0.5 • 0.5 •1 Weight 1 = 0.5, ? Output •0 •0 •0 •1 Weight 2 = 0.5 Networks of such neurons are Turing complete 1912 - 1954 Semilinear node input weight activation Add Squashing function Semilinear node: the output relation (squashing function) output 1 activation 0 threshold