Scribd
Upload
14 views6 pages

ML Module 1

The document discusses six common issues in machine learning: data quality and quantity, bias and fairness, overfitting and underfitting, feature engineering, hyperparameter tuning, and interpretable and explainable models. It then explains five applications of machine learning: image recognition, natural language processing, healthcare, recommendation systems, and fraud detection. Finally, it describes the steps to develop machine learning applications: problem definition, data collection, feature engineering, model selection and training, evaluation and validation, and fine-tuning and deployment.

Uploaded by

MSD
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
14 views6 pages

ML Module 1

The document discusses six common issues in machine learning: data quality and quantity, bias and fairness, overfitting and underfitting, feature engineering, hyperparameter tuning, and interpretable and explainable models. It then explains five applications of machine learning: image recognition, natural language processing, healthcare, recommendation systems, and fraud detection. Finally, it describes the steps to develop machine learning applications: problem definition, data collection, feature engineering, model selection and training, evaluation and validation, and fine-tuning and deployment.

Uploaded by

MSD
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
You are on page 1/ 6

1.

what are issues in machine learning


Ans Certainly, here are six common issues in machine learning:

I. Data Quality and Quantity: Machine learning models heavily rely on data for
training. Poor quality data or insufficient data can lead to inaccurate or biased models.
Cleaning and preprocessing data is often a time-consuming and critical step.

Ii. Bias and Fairness: Models can inadvertently learn biases present in the training
data, leading to unfair or discriminatory outcomes. Ensuring fairness and mitigating
bias is a significant ethical concern in machine learning.

iii. Overfitting and Underfitting: Overfitting occurs when a model learns the training
data too well, capturing noise and leading to poor generalization on new data.
Underfitting, on the other hand, happens when a model is too simple to capture the
underlying patterns in the data.

iv. Feature Engineering: Selecting and creating relevant features from raw data is
crucial for model performance. Poor feature selection can lead to suboptimal results,
and manual feature engineering can be time-intensive.

v. Hyperparameter Tuning: Machine learning algorithms have hyperparameters that


need to be set before training. Finding the right combination of hyperparameters can
be challenging and often requires experimentation.

vi . Interpretable and Explainable Models: Complex models like deep neural networks
can be highly accurate, but they are often difficult to interpret. Understanding why a
model makes a certain prediction is important for building trust and explaining
decisions to stakeholders.
2 Explain any five applications of Machine Learning?

Ans: Certainly, here are five applications of machine learning:

1. Image Recognition and Computer Vision:


Machine learning is used for tasks like object detection, image classification, and
facial recognition. Applications range from medical image analysis to self-driving cars,
where ML algorithms enable the recognition and interpretation of visual data.

2. Natural Language Processing (NLP):


NLP techniques allow machines to understand, interpret, and generate human
language. Applications include sentiment analysis, chatbots, language translation, and
text summarization.

3. Healthcare and Medical Diagnosis:


Machine learning assists in diagnosing diseases, predicting patient outcomes, and
identifying potential treatments. ML models analyze medical images, genomic data,
and patient records to improve diagnostics and personalized medicine.

4. Recommendation Systems:
ML powers recommendation engines in platforms like Netflix, Amazon, and Spotify.
These systems analyze user behavior to suggest relevant content, products, or music,
enhancing user experience and driving engagement.

5. Financial Services and Fraud Detection


Machine learning is used to detect fraudulent transactions and predict credit risk. ML
algorithms analyze large volumes of financial data to identify unusual patterns and
behaviors that could indicate fraudulent activity.
3. What is machine learning ? difference between machine learning &
data mining?
Ans

In the real world, we are surrounded by humans who can learn everything from
their experiences with their learning capability, and we have computers or
machines which work on our instructions. But can a machine also learn from
experiences or past data like a human does? So here comes the role of Machine
Learning.

Machine Learning is said to be a subset of artificial intelligence that is mainly


concerned with the development of algorithms which allow a computer to learn
from the data and past experiences on their own. The term machine learning
was first introduced by Arthur Samuel in 1959. We can define it in a
summarized way as:

“Machine learning enables a machine to automatically learn from data,

improve performance from experiences, and predict things without being

explicitly programmed.”
4. Explain the steps of developing Machine Learning applications
steps involved in developing Machine Learning applications:

​ Problem Definition:
● Clearly define the problem you want to solve with Machine
Learning.
● Identify the input data (features) and the desired output (target).
​ Data Collection:
● Gather relevant and sufficient data for training and testing the
model.
● Ensure data quality and perform data preprocessing (cleaning,
handling missing values, etc.).
​ Feature Engineering:
● Select and transform appropriate features from the raw data.
● Create new features if necessary to enhance the model's
performance.
​ Model Selection and Training:
● Choose a suitable Machine Learning algorithm based on the
problem type (classification, regression, etc.).
● Split the data into training and testing sets.
● Train the chosen model using the training data.
​ Evaluation and Validation:
● Evaluate the model's performance using metrics like accuracy,
precision, recall, or mean squared error, depending on the problem.
● Validate the model's performance on unseen data (testing set) to
assess its generalization ability.
​ Fine-Tuning and Deployment:
● Fine-tune the model by adjusting hyperparameters to improve its
performance.
● Once satisfied with the model's performance, deploy it to a
production environment for real-world use.

You might also like