You are on page 1of 6

Artificial Neural Networks (ANN)

• Artificial Neural Networks (ANNs) are machine


learning models inspired by the human brain's
structure and function.
• ANNs consist of interconnected nodes (neurons)
that process information similarly to human
neurons.
• Their primary purpose is to learn from data and
improve their performance through training.
• ANNs find applications in various fields, including
image recognition, speech recognition, and
natural language processing.
• A common type of ANN is the feedforward neural
network, which comprises input, hidden, and
output layers.
• In a feedforward neural network, the input layer
receives data, the hidden layer processes it, and
the output layer produces a result.

Reference: Introduction to Artificial Neural Networks - Analytics Vidhya. (n.d.). Retrieved


September 20, 2023, from https://www.analyticsvidhya.com/blog/2021/09/introduction-
to-artificial-neural-networks/
Architecture of Artificial Neural Networks

• ANNs (Artificial Neural Networks) are organized into layers, typically


including an input layer, one or more hidden layers, and an output layer.
• Neurons within each layer are connected to neurons in adjacent layers
through weighted connections.
• Activation functions are applied to these interconnected neurons to
compute outputs or activations.
• ANNs learn from data through iterative processes, including
backpropagation and gradient descent.
• During training, ANN weights are adjusted to minimize the difference
between predicted outputs and actual outputs in a process known as
optimization.
• The capability of ANNs to model complex relationships in data has
established them as a foundational tool in modern machine learning and
deep learning applications.

Reference: Introduction to Artificial Neural Networks - Analytics Vidhya. (n.d.). Retrieved September 20, 2023, from
https://www.analyticsvidhya.com/blog/2021/09/introduction-to-artificial-neural-networks/
Applications Of Artificial Neural Networks
• Image Classification: ANNs can classify images into
predefined categories, such as identifying animals in
photos.
• Sentiment Analysis: ANNs analyse text to determine
the sentiment (positive, negative, or neutral) expressed in
reviews or social media posts.
• Handwriting Recognition: ANNs recognize
handwritten characters and convert them into digital text.
• Credit Scoring: ANNs assess creditworthiness by
analysing financial data to predict the likelihood of loan
repayment.
• Recommendation Systems: ANNs power
personalized recommendations on platforms like Netflix,
suggesting movies or products based on user preferences. Reference: Introduction to Artificial Neural Networks -
Analytics Vidhya. (n.d.). Retrieved September 20, 2023,
from
https://www.analyticsvidhya.com/blog/2021/09/introducti
on-to-artificial-neural-networks/
Hyper parameters Tuning in Neural
Networks
Hyperparameter tuning in neural networks is the process of
finding the best values for the settings that are not learned from the
data but are set before training the network.
• Key hyperparameters include learning rate, batch size,
layer count, neuron count, activation functions, and
regularization strength.
• Tuning these hyperparameters is vital for achieving
optimal network performance.

Bayesian optimization is a more advanced method of hyperparameter tuning that uses a probability function based on
the hyperparameters and accuracy score to model the distribution of the hyperparameters and their impact on the model's performance

Reference: Hyperparameters Tuning in Neural Networks - Scaler Topics. (n.d.). Retrieved September
20, 2023, from https://www.scaler.com/topics/deep-learning/neural-network-hyperparameters-tuning/
Conclusion

• ANNs are like digital brains: They learn and solve complex problems, making them valuable for
various tasks.
• They're used in many areas: From recognizing pictures to understanding language and driving cars,
ANNs have practical applications.
• They keep improving: As technology advances, ANNs will become even more powerful and help
solve even tougher problems.
• They're part of our tech future: ANNs play a big role in the exciting future of computers and how
they can make our lives better.

You might also like