Scribd
Upload
2 views

Introduction to Deep Learning

Uploaded by

satyatiwari7407
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
2 views

Introduction to Deep Learning

Uploaded by

satyatiwari7407
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 6

Introduction to Deep

Learning
Explore the basics, comparisons, and applications of deep
learning. This presentation covers fundamental concepts and
real-world use cases.
Submitted to: Dr. Sunil Kumar Shukla

Submitted by: Tarun Tiwari (0901AI221070)


COURSE OUTCOMES

CO1. describe the fundamental concepts of Artificial Intelligence and Machine Learning.

CO2: design heuristics driven search solutions for real-world problems.

CO3. identify machine learning based real world problem.

CO4. design Artificial Intelligence enabled intelligent systems for solving real world

problems.

CO5. analyze Artificial Intelligence and machine learning algorithms.

CO6. evaluate the performance of Artificial Intelligence and machine learning

techniques.
What is Deep Learning?
 Deep Learning is a subset of Machine Learning based on artificial neural networks.

 It attempts to mimic the human brain in data processing and decision-making.

 It uses multiple layers (hence “deep”) to extract increasingly abstract features from raw data.

Key Components:

Neural Networks Activation Functions Backpropagation


CNNs and RNNs process Introduce non-linearity into Adjusts network weights to
complex data. models. minimize error.
ML vs. Deep Learning
Deep Learning differs from traditional ML in feature learning and data handling.

Machine Learning Deep Learning

• Works with small datasets • Requires large datasets

• Manual feature engineering • Automated feature extraction

• Works with small datasets • Requires large datasets.

• Training time is generally faster • Training takes longer because it is resource-intensive.


How Deep Learning Works?
A Deep Learning network consists of an input layer, hidden layers, and an output layer. Each layer plays a role
in processing data.
 Step 1: Input Data

Raw data like images, text, or sound is given to the model.

 Step 2: Hidden Layers Process Data

The model has many layers (like building blocks) that learn patterns in the data.

 Step 3: Output Prediction

The final layer gives the result (e.g., a label like "cat" or "not cat").

 Why “Deep”?

Because the model has many layers between input and output!

 Key Point:

The more layers, the better the model can understand complex data.
Applications of Deep
Learning
Deep Learning is applied across computer vision, NLP,
healthcare, and autonomous vehicles. It is transforming
industries.

Computer Vision NLP


Object detection, facial Language translation,
recognition. chatbots.

Healthcare Autonomous Vehicles:


Disease prediction, Self-driving cars
medical imaging.

You might also like