Introduction to Artificial Intelligence_ Lec 9
- 2. • ANNs Architecture • ANN Advantages and Disadvantages
- 3. • ANNs are computing systems based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. • Each connection can transmit a signal from one artificial neuron to another. An artificial neuron that receives a signal can process it and then signal additional artificial neurons connected to it. • Deep learning involves the study of complex ANN-related algorithms.
- 4. • • Neurons • The building blocks for ANNs are neurons (also known as artificial neurons, nodes, or perceptrons). • Neurons have one or more inputs and one output. It is possible to build a network of neurons to compute complex logical propositions. • Activation functions in these neurons create complicated, nonlinear functional mappings between the inputs and the output. • As shown in Figure, a neuron takes an input (x1, x2…xn), applies the learning parameters to generate a weighted sum (z), and then passes that sum to an activation function (f) that computes the output f(z).
- 6. Layers • In order to handle more complex structures, we have multiple layers of such neurons. • Figure shows an architecture of an ANN with an input layer, an output layer, and a hidden layer.
- 7. • The input layer takes input from the dataset and is the exposed part of the network. A neural network is often drawn with an input layer of one neuron per input value (or column) in the dataset. The neurons in the input layer simply pass the input value though to the next layer. • Hidden layers. Layers after the input layer are called hidden layers because they are not directly exposed to the input. The simplest network structure is to have a single neuron in the hidden layer that directly outputs the value. • A multilayer ANN is capable of solving more complex machine learning–related tasks due to its hidden layer(s). • ANNs with many hidden layers (more than three) are known as deep neural networks. Multiple hidden layers allow deep neural networks to learn features of the data in a so-called feature hierarchy, because simple features recombine from one layer to the next to form more complex features. • Output layer. The final layer is called the output layer; it is responsible for outputting a value or vector of values that correspond to the format required to solve the problem.
- 8. Neuron weights: • Neuron weight: Determines the strength of the connection between neurons. • Higher weight magnitude: Indicates a stronger influence of one neuron on another. • Weight near zero: Means the input has little to no effect on the output. • Negative weight: Means increasing the input decreases the output.
- 9. Deep neural network: ANNs with more than a single hidden layer are often called deep networks.
- 10. Advantages and Disadvantages Advantages of ANN: • Captures Nonlinearity: Effectively models complex, nonlinear relationships between variables. • Rich Representations: Learns intricate patterns and features from data. • Handles Large Data & Features: Performs well with a high number of input features and large datasets. • Flexible Applications: Used across various AI domains, including reinforcement learning and NLP.
- 11. Advantages and Disadvantages Disadvantages of ANN: • Poor Interpretability: Difficult to understand and explain model decisions. • Requires Large Datasets: Not well-suited for small datasets. • Hyperparameter Tuning: Involves extensive tweaking and trial-and-error. • Topology Selection Challenge: Choosing the right architecture and algorithm is complex. • Computationally Expensive: Training can be time-consuming and resource- intensive.
- 12. • Code file: Creating an Artificial Neural Network Model in Python.ipynb
- 13. • What are the ANN Advantages and disadvantages?