UNIT 2

(Artificial Intelligence &

Machine Learning)
Introduction to Machine
Learning
What is Machine Learning?
▪ “Learning is any process by which a system improves performance from
experience.” - Herbert Simon

▪ Definition by Tom Mitchell (1998):

▪ Machine Learning is the study of algorithms that
▪ improve their performance P
▪ at some task T
▪ with experience E.
▪ A well-defined learning task is given by <P,T,E>
 Machine Learning Traditional Programming

Machine Learning is a subset of artificial intelligence(AI) that In traditional programming, rule-based code is written by the
focus on learning from data to develop an algorithm that can be developers depending on the problem statements
used to make a prediction.

Machine Learning uses a data-driven approach, It is typically Traditional programming is typically rule-based and
trained on historical data and then used to make predictions on deterministic. It hasn’t self-learning features like Machine
new data. Learning and AI.

ML can find patterns and insights in large datasets that might be Traditional programming is totally dependent on the
difficult for humans to discover. intelligence of developers. So, it has very limited capability.

Machine Learning is the subset of AI. And Now it is used in Traditional programming is often used to build applications and
various AI-based tasks like Chatbot Question answering, self- software systems that have specific functionality.
driven car., etc.
Machine Learning lifecycle:
▪ The lifecycle of a machine learning project involves a series of steps that
include:

1. Study the Problems: The first step is to study the problem. This step
involves understanding the business problem and defining the objectives
of the model.
2. Data Collection: When the problem is well-defined, we can collect the
relevant data required for the model. The data could come from various
sources such as databases, APIs, or web scraping.
3. Data Preparation: When our problem-related data is collected. then it is a
good idea to check the data properly and make it in the desired format so
that it can be used by the model to find the hidden patterns. This can be
done in the following steps:
Machine Learning lifecycle:
▪ Data cleaning
▪ Data Transformation
▪ Explanatory Data Analysis and Feature Engineering
▪ Split the dataset for training and testing.
4. Model Selection: The next step is to select the appropriate machine
learning algorithm that is suitable for our problem. This step requires
knowledge of the strengths and weaknesses of different algorithms.
Sometimes we use multiple models and compare their results and select
the best model as per our requirements.
Machine Learning lifecycle:
5. Model building and Training: After selecting the algorithm, we have to
build the model.
In the case of traditional machine learning building mode is easy it is just a
few hyperparameter tunings.
In the case of deep learning, we have to define layer-wise architecture
along with input and output size, number of nodes in each layer, loss
function, gradient descent optimizer, etc.
After that model is trained using the preprocessed dataset.
6. Model Evaluation: Once the model is trained, it can be evaluated on the
test dataset to determine its accuracy and performance.
▪ A classic example of a task that requires machine learning: It is very hard
to say what makes a 2
▪ Some more examples of tasks that are best solved by using a learning
algorithm
▪ Recognizing patterns:
▪ – Facial identities or facial expressions
▪ – Handwritten or spoken words
▪ – Medical images

▪ Generating patterns:
▪ Generating images or motion sequences
▪ Recognizing anomalies:
▪ – Unusual credit card transactions
▪ – Unusual patterns of sensor readings in a nuclear power plant

▪ Prediction:
▪ – Future stock prices or currency exchange rates
Introduction to AI
▪ Artificial Intelligence (AI) is a branch of computer science that
focuses on creating machines or systems capable of performing
tasks that typically require human intelligence. These tasks
include learning, reasoning, problem-solving, perception,
language understanding, and decision-making. The ultimate goal
of AI is to develop machines that can exhibit intelligence similar
to or even surpassing human intelligence.
Types of AI
▪ AI can be broadly categorized into two types:
▪ Narrow AI (or Weak AI)
Narrow AI is designed to perform a specific task or a
set of tasks, such as speech recognition, image recognition,
or playing chess
▪ General AI (or Strong AI)
▪ General AI, on the other hand, refers to machines with
the ability to understand, learn, and apply knowledge
across various domains, similar to human intelligence.
Components of AI includes
1. Machine Learning (ML): It is a subset of AI that involves the
development of algorithms and statistical models that enable computers
to improve their performance on a task through experience.
2. Deep Learning: This is a subfield of machine learning that involves
neural networks with multiple layers (deep neural networks). Deep
learning has proven to be highly effective in tasks such as image and
speech recognition, natural language processing, and more.
3. Natural Language Processing (NLP): NLP enables computers to
understand, interpret, and generate human language. It is crucial for
applications like chatbots, language translation, and sentiment analysis.
4. Computer Vision: This field focuses on enabling machines to interpret
and understand visual information from the world, such as images and
videos. Applications include facial recognition, object detection, and
autonomous vehicles.
5. Robotics: Integrating AI with robotics allows machines to interact with
the physical world, perform tasks, and make decisions based on sensory
input.
6. Expert Systems: These are computer systems designed to mimic the
AI/ML
▪ Machine learning is making great strides
▪ Large, good data sets
▪ Compute power
▪ Progress in algorithms
▪ Many interesting applications
▪ commericial
▪ scientific
▪ Links with artificial intelligence
▪ However, AI  machine learning
Machine Learning Tasks
▪ Supervised learning
▪ regression: predict numerical values
▪ classification: predict categorical values, i.e., labels
▪ Unsupervised learning
▪ clustering: group data according to "distance"
▪ association: find frequent co-occurrences
▪ link prediction: discover relationships in data
▪ Reinforcement learning
Machine Learning
Algorithms
▪ Regression:
Ridge regression, Support Vector Machines, Random Forest,
Multilayer Neural Networks, Deep Neural Networks, ...

▪ Classification:
Naive Base, , Support Vector Machines,
Random Forest, Multilayer Neural Networks,
Deep Neural Networks, ...

▪ Clustering:
k-Means, Hierarchical Clustering, ...
Issues
▪ Many machine learning/AI projects fail
(Gartner claims 85 %)

▪ Ethics, e.g., Amazon has/had

sub-par employees fired by an AI
automatically
Reasons for failure
▪ Asking the wrong question
▪ Trying to solve the wrong problem
▪ Not having enough data
▪ Not having the right data
▪ Having too much data
▪ Hiring the wrong people
▪ Using the wrong tools
▪ Not having the right model
▪ Not having the right yardstick
Expert Systems:
▪ Expert systems are computer programs designed to emulate the
decision-making ability of a human expert in a specific domain. They use
a knowledge base of human expertise and an inference engine to
provide solutions or make decisions. Expert systems are applied in
various fields, including:
• Medical Diagnosis: Expert systems can assist medical professionals in
diagnosing diseases based on symptoms and patient history.
• Financial Planning: They can provide advice on investment strategies
and financial planning based on expert knowledge.
• Troubleshooting: Expert systems can help users diagnose and solve
technical problems by guiding them through a series of questions.
Augmented Reality:
▪ Augmented Reality (AR) combines digital information with
the user's real-world environment. AI plays a role in
enhancing AR experiences through:
• Object Recognition: AI algorithms can recognize and
augment real-world objects in the user's view.
• Gesture Recognition: AI helps interpret user gestures for
interactive AR applications.
AI in Different Fields:
• Natural Language Processing (NLP): Used in
chatbots, language translation, sentiment analysis,
and voice recognition.
• Healthcare: AI is applied for diagnostics, drug
discovery, personalized medicine, and patient
management.
• Agriculture: AI aids in precision farming, crop
monitoring, and pest control.
• Social Media Monitoring: AI is used to analyze
social media data for sentiment analysis, trend
prediction, and content moderation.
Tools and Techniques for Implementing AI:

• Machine Learning Frameworks: TensorFlow,

PyTorch
• Development Platforms: Jupyter Notebooks,
Google Colab.
• Data Preprocessing: Pandas, NumPy.
• Natural Language Processing Tools: NLTK,
spaCy.
AI-powered Products:
• Google Translator: Uses machine learning for
language translation.
• Driverless Cars: AI algorithms enable autonomous
vehicles to navigate and make decisions.
• Voice Assistants (Alexa, Siri): Use natural
language processing to understand and respond to
user commands.
• ChatGPT: Utilizes a language model for generating
human-like text responses.
 Current trends and opportunities
1. Development in predictive analytics
2. Large Language Models (LLM)
3. Information security (InfoSec)
4. Launch of better autonomous systems
5. Art through NFTs
6. Digital avatars
7. Military weapons
8. Healthcare
9. Explainable AI (XAI): Enhancing transparency and interpretability of AI
models.
10. Edge AI: Processing AI tasks on devices rather than relying solely on
cloud computing.
11. AI Ethics and Bias Mitigation: Ensuring responsible and fair AI
development.
 Job roles and skill set
SKill Set
● Programming languages (Python, R, Java are the most necessary)
● Linear algebra and statistics
● Signal processing techniques
● Neural network architectures
● Machine Learning algorithms

Job Roles
● Machine Learning Engineer
● Data scientist
● Robotics scientist
● Research
● NLP Engineer
● Computer Vision Engineer.