Machine Learning (ML)

10.10.2024

Machine Learning (ML)

Why in the news?                                                                                                                                                                                                                                     

The 2024 Nobel Prize in physics has been awarded to John Hopfield and Geoffrey Hinton for foundational discoveries and inventions that enable machine learning with artificial neural networks.

About Machine Learning (ML):

• It is a branch of Artificial Intelligence (AI) focused on building computer systems that learn from data.
• It allows computer systems to continuously adjust and enhance themselves as they accrue more “experiences.”
• ML algorithms are trained to find relationships and patterns in data.
• Using historical data as input, these algorithms can make predictions, classify information, cluster data points, reduce dimensionality and even generate new content.

○Examples of the latter, known as generative AI, include OpenAI's ChatGPT, Anthropic's Claude and GitHub Copilot.

• Training ML algorithms often demands large amounts of high-quality data to produce accurate results.

Applications of Machine Learning:

• It is widely applicable across many industries. For example, e-commerce, social media and news organizations use recommendation engines to suggest content based on a customer's past behavior.
• In self-driving cars, ML algorithms and computer vision play a critical role in safe road navigation.
• In healthcare, ML can aid in diagnosis and suggest treatment plans.
• Other common ML use cases include fraud detection, spam filtering, malware threat detection, predictive maintenance, and business process automation.

What is Deep Learning?

• It is a method in AI that teaches computers to process data in a way that is inspired by the human brain.
• It is a subset of ML which simulates the complex decision-making power of the human brain.
• Deep learning models can recognize complex patterns in pictures, text, sounds, and other data to produce accurate insights and predictions.
• Deep learning methods are used to automate tasks that typically require human intelligence, such as describing images or transcribing a sound file into text.

Machine Learning Vs. Deep Learning

While machine learning involves training algorithms with structured data and often requires human input for feature extraction, deep learning automates feature discovery using multi-layered neural networks, making it more powerful for complex tasks, especially when large datasets are available.

About the Artificial Neural Network (ANN)

• It is a mathematical model that uses a network of interconnected nodes to mimic the human brain's neurons and process data.
• ANNs are a type of machine learning (ML) and deep learning that can learn from mistakes and improve over time.
• They are used in artificial intelligence (AI) to solve complex problems, such as recognizing faces or summarizing documents.

Key features of ANNs

Structure

• ANNs are made up of layers of nodes, each containing an activation function. The nodes are interconnected, with each node in a layer connected to many nodes in the previous and next layers.

Learning

• ANNs are adaptive and learn from their mistakes using a backpropagation algorithm.
• They modify themselves as they learn, with inputs that contribute to the right answers weighted higher.

Output

The output of the ANN is produced by the final layer of nodes. The output is usually a numerical prediction about the information the ANN received.

Types of ANNs

• Feedforward Neural Networks (FNNs): The simplest type, where connections do not form cycles. Data moves in one direction from input to output.
• Convolutional Neural Networks (CNNs): Specialized for processing grid-like data such as images. They use convolutional layers to automatically and adaptively learn spatial hierarchies of features.
• Recurrent Neural Networks (RNNs): Designed for sequential data, such as time series or natural language. They have connections that form cycles, allowing them to maintain a memory of previous inputs.
• Autoencoders: Used for unsupervised learning, these networks aim to learn a compressed representation of the input data.

Applications of Artificial Neural Networks:

• Image and video recognition (e.g., facial recognition systems)
• Speech recognition (e.g., virtual assistants like Siri and Alexa)
• Natural language processing (e.g., language translation)
• Medical diagnostics (e.g., detecting diseases from medical images)
• Autonomous vehicles (e.g., self-driving car navigation)

                                                                 Source: The Hindu

Consider the following statements regarding Machine Learning (ML):

1. It is a branch of Artificial Intelligence (AI) focused on building computer systems that learn from data.

2. Using historical data as input, these algorithms can make predictions, classify information, and generate new content.

Which of the statements given above is/are correct?

A.1 only

B.2 only

C.Both 1 and 2

D.Neither 1 nor 2

Answer B