TYPES OF

NEURON
CONNECTION
ARCHITECTUR
E

LEARNING
Basic types of neuron connection architectures
The arrangement of neuron to form layer and the connection pattern form within and between layer is
called network architecture
• Single-layer feed-forward network;
• Multilayer feed-forward network;
• single node with itS own feedback;
• Single-layer recurrent network;
• Mulrilayer recurrent network.
Description
Feedforward network: If no neuron in the output layer is an input to the node in same layer or its
preceding layers.
Feedback network: When output can be directed back as input to same or preceding layers nodes
Fully connected networks: Every output from one layer is connected to each and every node in the
next layer
Lateral Feedback: If the output of the processing element is directed back as input to processing
elements in the same layer
Recurrent Neural Network: Feedback network with closed loop.
Competitive Layer: They have fixed weight of This net is called Maxnet. unsupervised learning
network
Disadvantage of FFNN

• Handle only current state but need previous state.

• Absent memory element.
Recurrent neural network
• It has memory element.
• It can handle sequential data.
• Recurrent Neural Network(RNN) are a type of Neural Network where
the output from previous step are fed as input to the current step.
• In traditional neural networks, all the inputs and outputs are
independent of each other, but in cases like when it is required to
predict the next word of a sentence, the previous words are required
and hence there is a need to remember the previous words.
Single layer feed forward neural network

• Feed Forward Neural Network is an artificial

neural network.
• the connections between nodes does not form a
cycle.
• Information is only processed in one direction.
• The feed forward model is the simplest form of
neural network
 Multilayer feed forward neural network

• A multilayer feedforward neural network is

an interconnection of perceptions in which
data and calculations flow in a single
direction, from the input data to the
outputs.
• A Multi-Layer Perceptron (MLP) contains
one or more hidden layers (apart from one
input and one output layer). While a single
layer perceptron can only learn linear
functions, a multi-layer perceptron can
also learn non - linear functions.
Representation of types of network
 Learning
The main property of an ANN is its capability to learn. Learning or training is a process by means of which a
neural network adapts itself to a stimulus by making proper parameter adjustment resulting in the production
of desired response

Two types
1. Parameter learning: It updates the connecting weights in a neural net.
2. Strncture learning: It focuses on the change in network structure (which includes the number of processing
elements as well as their connection types).

The above two types of learning can be performed simultaneously or separately.

Other Learning Categories
• Supervised learning
• Unsupervised learning
• Reinforcement learning
Supervised Learning
• The learning here is performed with the help of a teacher
• All these real-time events involve supervised learning methodology.
• In ANNs following the supervised learning, each input vector requires a
corresponding target vector, which represents the desired output.
• The input vector along with the target vector is called training pair
• The network here is informed precisely about what should be emitted as output.
• During training. the input vector is presented to the network, which results in an
output vector.
• This output vector is the actual output vector. Then the actual output vector is
compared with the desired (target) output vector
• If there exists a difference between the two output vectors then an error signal is
generated by the network.
• The error signal is used for adjustment of weights until actual output matches the
desired output
 Unsupervised Learning
• The learning here is performed without the help of a teacher.
• In ANNs following unsupervised learning, the input vectors of similar type are grouped without the use
of training data to specify how member of each group looks or to which group number belongs.
• In training process network receives input pattern and organize these patterns to form cluster.
• When new pattern is applied, the neural network gives an output response indicating the class to which
input pattern belongs
• If class not found, then new class is generated.
• Self organizing networks.
 Reinforcement Learning
• This learning process is similar to supervised learning. In the case of supervised learning, the correct target output
values are known for each input pattern. But, in some cases, less information might be available.
For example, the network might be told chat its actual output is only "50% correct" or so. Thus, here only
critic information is available, nor the exact information.
• The reinforcement learning is also called learning with a critic as opposed to learning with a teacher,
Important Terminologies in ANN
• Weights: In the architecture of an ANN, each neuron is connected ro other neurons by means of
directed communication links, and each communication link is associated with weights.
• The weight can be represented in terms of matrix. The weight matrix can also be called connection matrix.

• Wij is the weight from processing element “i" (source node) to processing element "j' (destination node).
Bias
• The bias included in the network has its impact in calculating the net input. The bias is included by adding a
component x0= 1 to the input vector X, the input vector becomes

Consider the equation of straight line Types of Bias

y=mx+c 1. Positive bias: helps in increasing the net
x=input input of network
m=weight 2. Negative Bias: helps in decreasing net
c=bias input of network
w=weight
Threshold
It is a set value based upon which the final output of the network may be calculated.

Learning rate
It is used to control amount of weight adjustment at each step of training, the learning rate ranges from 0 to 1,
determines rate of learning at each time stamp.