LECTURE FIVE ARTIFICIAL NEURAL NETWORKS AND NEUROSEMANTICS 人工神经元网络以及神经语义学
ARTIFICIAL NEURAL NETWORKS AND NEUROSEMANTICS 人工神经元网络以及神经语义学
THE CONNECTIONS BETWEEN THIS LECTURE AND THE LAST ONE If eliminativism is right, then we cannot reduce types of mental states to anything else. That means, the natural kinds of any type of mental states cannot survive a strict implementation of an eliminativist program o Somehow similar to this case from an eliminativist perspective, the Great French Revolution is not a legitimate label which can pick out a single historical event. Rather, it should be viewed as a label attached to a loose collection of the behaviors of numerous individuals. Though historians need to rely on this label when the behaviors of individuals are epistemologically inaccessible to them; they also need to be prepared to abandon this label when new data are available
If eliminativism is right, then we cannot reduce types of mental states to anything else. That means, the natural kinds of any type of mental states cannot survive a strict implementation of an eliminativist program. Somehow similar to this case: from an eliminativist perspective, the Great French Revolution is not a legitimate label which can pick out a single historical event. Rather, it should be viewed as a label attached to a loose collection of the behaviors of numerous individuals. Though historians need to rely on this label when the behaviors of individuals are epistemologically inaccessible to them; they also need to be prepared to abandon this label when new data are available
SO THE MORAL IS Philosophers of mind and cognitive scientists need to be prepared to abandon the mental vocabulary when new data about humans neural systems are available
Philosophers of mind and cognitive scientists need to be prepared to abandon the mental vocabulary when new data about human’ s neural systems are available
THREE TASKS LEFTIN THE AGENDA 1. To learn something from Neuroscience To seek some possibility of making the neurological story more universal(with, say, the help of AI) 3. To try to reconstruct the mental architecture out of the findings in neural science and Al
1. To learn something from Neuroscience; 2. To seek some possibility of making the neurological story more universal (with, say, the help of AI) 3. To try to reconstruct the mental architecture out of the findings in neural science and AI
WHAT NEUROSCIENCE CAN TELL By definition,"Neurons are basic signaling units of the nervous system of a living being in which each neuron is a discrete cell whose several processes are from its cell bod The biological neuron has four main regions to its structure. The cell body, or soma. has two offshoots from it. The dendrites(树突 and the axon(轴突 end in pre-synaptic terminals(突触前末 is). The cell body is the heart of the cell It contains the nucleolus(细胞核)and maintains protein synthesis(蛋台质合 Ai). A neuron has many dendrites which look like a tree structure, receives signals from other neurons
By definition, “Neurons are basic signaling units of the nervous system of a living being in which each neuron is a discrete cell whose several processes are from its cell body” . The biological neuron has four main regions to its structure. The cell body, or soma, has two offshoots from it. The dendrites (树突)and the axon (轴突) end in pre-synaptic terminals(突触前末 端). The cell body is the heart of the cell. It contains the nucleolus(细胞核) and maintains protein synthesis(蛋白质合 成). A neuron has many dendrites, which look like a tree structure, receives signals from other neurons
MOREOVER A single neuron usually has one axon, which expands off from a part of the cell body. This I called the axon hillock(#h k). The axon main purpose is to conduct electrical signals generated at the axon hillock down its length. These signals are called action potentials(动作电位). e The other end of the axon may split into several branches, which end in a pre-synaptic terminal. The electrical signals(action potential) that the neurons use to convey the information of the brain are all identical. The brain can determine which type of information is being received based on the path of the signal e Just similar to this case: I will send the some message to different medias, and the authority of each media will change the weight of what I said from the audience perspective
A single neuron usually has one axon, which expands off from a part of the cell body. This I called the axon hillock(轴丘). The axon main purpose is to conduct electrical signals generated at the axon hillock down its length. These signals are called action potentials(动作电位). The other end of the axon may split into several branches, which end in a pre-synaptic terminal. The electrical signals (action potential) that the neurons use to convey the information of the brain are all identical. The brain can determine which type of information is being received based on the path of the signal. Just similar to this case: I will send the some message to different medias, and the authority of each media will change the weight of what I said from the audience perspective
The Mathematical model Fixed input xo=± Once modeling an artificial functional model from 100—8080= bk(bias the biological neuron, we must take into account three basic components. First of all, the synapses of the biological neuron are modeled as weights. Let's n10-2wkI is the one which interconnects the neural networ remember that the synapse of the biological neuron Activation and gives the strength of the connection. For an Finction artificial neuron, the weight is a number, and 12O—用 k represents the synapse. A negative weight reflects an 卡9( Jk inhibitory connection, while positive values designate excitatory connections. The following components of the model represent the actual activity of the neuron cell. All inputs are summed altogether and modified by the weights. This activit k is referred as a linear combination. Finally, an Input Synaptic activation function controls the amplitude (it +o ) of Weights the output. For example, an acceptable range of output is usually between o and 1, or it could be-1 and l
Once modeling an artificial functional model from the biological neuron, we must take into account three basic components. First of all, the synapses of the biological neuron are modeled as weights. Let’s remember that the synapse of the biological neuron is the one which interconnects the neural network and gives the strength of the connection. For an artificial neuron, the weight is a number, and represents the synapse. A negative weight reflects an inhibitory connection, while positive values designate excitatory connections. The following components of the model represent the actual activity of the neuron cell. All inputs are summed altogether and modified by the weights. This activity is referred as a linear combination. Finally, an activation function controls the amplitude (值幅)of the output. For example, an acceptable range of output is usually between 0 and 1, or it could be -1 and 1
Activation functions(激发函数) As mentioned previously, the activation function acts as a squashing function(压缩函数), such that the output of a neuron in a neural network is between certain values(usually o and 1, or-1 and 1). In general, there are three types of activation functions, denoted byΦ(
As mentioned previously, the activation function acts as a squashing function(压缩函数), such that the output of a neuron in a neural network is between certain values (usually 0 and 1, or -1 and 1). In general, there are three types of activation functions, denoted by Φ(.)
Threshold function(阈值函数) First there is the Threshold 1in20 Function which takes on a 0if<0 value of o if the summed input is less than a certain threshold value(v), and the value l if the summed input is greater than or equal to the threshold value
First, there is the Threshold Function which takes on a value of 0 if the summed input is less than a certain threshold value (v), and the value 1 if the summed input is greater than or equal to the threshold value
Piecewise-Linear function(方形分片线 性函数) 1> Secondly, there is the Piecewise-Linear function. This function c=-+> again can take on the values of o or l, but can also take on values 1 between that depending on the amplification factor in a certain region of linear operation
Secondly, there is the Piecewise-Linear function. This function again can take on the values of 0 or 1, but can also take on values between that depending on the amplification factor in a certain region of linear operation