Scribd
Upload
4 views2 pages

AI Fundamentals: Neural Networks & Ethics

The document outlines key concepts in AI, including the structure of neural networks, types of machine learning, and the K-Means algorithm. It also discusses trusted AI principles, the workings of expert systems, and the ethical considerations in AI. Additionally, it highlights the integration of AI with IoT (AIoT) for data analysis and automated decision-making.

Uploaded by

kusumithashemathkar
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
4 views2 pages

AI Fundamentals: Neural Networks & Ethics

The document outlines key concepts in AI, including the structure of neural networks, types of machine learning, and the K-Means algorithm. It also discusses trusted AI principles, the workings of expert systems, and the ethical considerations in AI. Additionally, it highlights the integration of AI with IoT (AIoT) for data analysis and automated decision-making.

Uploaded by

kusumithashemathkar
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

MODULE 3 & MODULE 4 – AI ELABORATED

NOTES

MODULE 3

1. Basic Neural Network Model


A neural network is inspired by the human brain. It consists of neurons connected in layers. The
input layer receives raw data, hidden layers perform computations using weights and activation
functions, and the output layer provides final predictions. Neural networks are used in image
recognition, speech processing, and predictions.

2. Machine Learning as Task, Performance and Experience


According to Tom Mitchell, learning happens when performance improves with experience. Task
defines what the system does, Performance measures accuracy or efficiency, and Experience
refers to training data. Example: Email spam detection improves accuracy when trained on more
labeled emails.

3. Types of Machine Learning


Supervised Learning uses labeled data for prediction. Unsupervised Learning finds hidden patterns
without labels. Reinforcement Learning learns through rewards and penalties.

4. K-Means Algorithm
K-Means is an unsupervised clustering algorithm that groups data into K clusters. Steps include
selecting K, assigning points to nearest centroid, recalculating centroids, and repeating until
stability. Merits: Simple, fast, scalable. Demerits: Sensitive to initial centroids and outliers.

5. Linear Equation Example


Monthly rental cost = Fixed cost + Variable cost. C = 20000 + 10000x where x is number of
employees.

6. Decision Tree Creation Steps


Select dataset, choose best attribute using information gain, split dataset, and repeat until
classification is complete.

MODULE 4

1. Trusted AI Principles
Fairness ensures no discrimination. Transparency explains AI decisions. Privacy protects data.
Reliability ensures consistent and safe operation.

2. Expert System
An expert system mimics human experts using a knowledge base, inference engine, and user
interface.

3. Ethics in AI
Ethics ensures responsible usage, protects privacy, prevents bias, promotes transparency, and
builds trust.
4. Working of Expert System
User inputs data, inference engine applies rules, system provides solution with explanation.

5. Risks of AI Methods
Incorrect goals, biased data, lack of control, and misuse can lead to harmful results.

6. AIoT
AIoT combines AI and IoT. Sensors collect data, AI analyzes it, and automated decisions are
executed.

You might also like