DL Syllabus

 

Code

Category

L

T

P

C

I.M

E.M

Exam

 

SOC

-

--

3

1.5

15

35

3 Hrs.

 

PYTHON: DEEP LEARNING

INFORMATION TECHNOLOGY

Skill Oriented Course

Pre-requisite knowledge :

1

• Exploratory data analysis: Collecting, importing, pre-processing, organizing, exploring, analyzing data and deriving insights from data https://infyspringboard.onwingspan.com/web/en/app/toc/lex_auth_012666909428129792728_shared/ overview

• Data visualization using Python: Data visualization functions and plots https://infyspringboard.onwingspan.com/web/en/app/toc/lex_auth_0126051913436938241455_shared /overview

• Regression analysis: Regression, types, linear, polynomial, multiple linear, Generalized linear regression models https://infyspringboard.onwingspan.com/web/en/app/toc/lex_auth_01320408013336576065_shared/o verview

• Clustering using Python: Clustering, techniques, Assessment and evaluation https://infyspringboard.onwingspan.com/web/en/app/toc/lex_auth_0130441799423426561190_shared /overview

• Machine learning using Python: Machine learning fundamentals, Regression, classification, clustering, introduction to artificial neural networks https://infyspringboard.onwingspan.com/web/en/app/toc/lex_auth_012600400790749184237_shared/ overview

• Time series analysis : Patterns, decomposition models, smoothing time, forecasting data https://infyspringboard.onwingspan.com/web/en/app/toc/lex_auth_0126051804744253441280_shared /overview  

 

Course Outcomes: By the end of this lab sessions Students can able to

S.No

Outcome

Knowledge Level

1

Demonstrate the basic concepts fundamental learning techniques and layers.

K3

2

Discuss the Neural Network training, various random models.

K3

3

Apply various optimization algorithms to comprehend different activation

K3

4

functions to understand hyper parameter tuning

K3

5

Build a convolutional neural network, and understand its application to build a  recurrent neural network, and understand its usage to comprehend auto encoders to briefly explain transfer learning 

K3

 

SYLLABUS

Note: There are online courses indicated in the reference links section. Learners need to go through the contents in order to perform the given exercises

Exp No

List of Experiments:

1

Course name : .Build a Convolution Neural Network for Image Recognition.

Go through the modules of the course mentioned and answer the self-assessment questions given in the link below at the end of the course.

Self-Assessment - Deep Learning - Viewer Page | Infosys Springboard (onwingspan.com)

2

Module name : Understanding and Using ANN : Identifying age group of an actor

Exercise : Design Artificial Neural Networks for Identifying and Classifying an actor using Kaggle Dataset.

https://infyspringboard.onwingspan.com/web/en/viewer/webmodule/lex_auth_012776492416663552259_shared?collectionId=lex_auth_01274814254931148859_share d&collectionType=Course

3

Module name : Understanding and Using CNN : Image recognition

Exercise: Design a CNN for Image Recognition which includes hyper parameter tuning.

https://infyspringboard.onwingspan.com/web/en/viewer/webmodule/lex_auth_012785694443167744910_shared?collectionId=lex_auth_01274814254931148859_share d&collectionType=Course

4

Module name : Predicting Sequential Data

Exercise: Implement a Recurrence Neural Network for Predicting Sequential Data.

https://infyspringboard.onwingspan.com/web/en/viewer/webmodule/lex_auth_01279144948849868822_shared?collectionId=lex_auth_01274814254931148859_shared &collectionType=Course

5

Module Name: Removing noise from the images

Exercise: Implement Multi-Layer Perceptron algorithm for Image denoising hyperparameter tuning.

https://infyspringboard.onwingspan.com/web/en/viewer/webmodule/lex_auth_012792058258817024272_shared?collectionId=lex_auth_01274814254931148859_share d&collectionType=Course

6

Module Name: Advanced Deep Learning Architectures

Exercise: Implement Object Detection Using YOLO.

https://infyspringboard.onwingspan.com/web/en/viewer/webmodule/lex_auth_013102923373297664873_shared?collectionId=lex_auth_01274814254931148859_share d&collectionType=Course

7

Module Name: Optimization of Training in Deep Learning

Exercise Name: Design a Deep learning Network for Robust Bi-Tempered Logistic Loss.

https://infyspringboard.onwingspan.com/web/en/viewer/webmodule/lex_auth_013107917226680320184_shared?collectionId=lex_auth_01274814254931148859_share d&collectionType=Course

8

Module name: Advanced CNN

Exercise: Build AlexNet using Advanced CNN.

https://infyspringboard.onwingspan.com/web/en/viewer/webmodule/lex_auth_013111844422541312984_shared?collectionId=lex_auth_01274814254931148859_share d&collectionType=Course

9

Module name: Autoencoders Advanced

Exercise: Demonstration of Application of Autoencoders.

https://infyspringboard.onwingspan.com/web/en/viewer/webmodule/lex_auth_0131164551289896962081_shared?collectionId=lex_auth_01274814254931148859_shar ed&collectionType=Course

10

Module name: Advanced GANs.

Exercise: Demonstration of GAN

https://infyspringboard.onwingspan.com/web/en/viewer/webmodule/lex_auth_0131155456664289281901_shared?collectionId=lex_auth_01274814254931148859_shar ed&collectionType=Course

11

Module name : Capstone project

Exercise : Complete the requirements given in capstone project.

Description: In this capstone, learners will apply their deep learning knowledge and expertise to a real world challenge

https://infyspringboard.onwingspan.com/web/en/viewer/webmodule/lex_auth_013119291805696000651_shared?collectionId=lex_auth_01274814254931148859_share d&collectionType=Course

12

Module name : Capstone project

Exercise : Complete the requirements given in capstone project

https://infyspringboard.onwingspan.com/web/en/viewer/webmodule/lex_auth_013119291805696000651_shared?collectionId=lex_auth_01274814254931148859_share d&collectionType=Course

 

Reference Books:

1

Goodfellow, I., Bengio,Y., and Courville, A., Deep Learning, MIT Press, 2016. 

2

Bishop, C., M., Pattern Recognition and Machine Learning, Springer, 2006.

3

Navin Kumar Manaswi, “Deep Learning with Applications Using Python”, Apress, 2018.

Web Links: [Courses mapped to Infosys Springboard platform]

1

https://infyspringboard.onwingspan.com/en/app/toc/lex_auth_012782105116811264219_shared/contents   [Introduction to Deep Learning]

2

https://infyspringboard.onwingspan.com/web/en/viewer/webmodule/lex_auth_013119291805696000651_shared  [Deep learning for Developers]

Comments

Post a Comment

Popular posts from this blog

11. List of Capstone Projects for SOC - Deep Learning

 List of Capstone Projects for SOC - Deep Learning  1. Build your Own Neural Net from Scratch. 2. Image Classification with CIFAR-10 Dataset.(Multi Class Classification) CNN 3. Human Face Detection.( detecting the bounding boxes of the human faces from a given Image)  YOLO  4. Traffic Sign Classification.(Collect Various traffic Signal Images and train Neural Network Model) CNN 5. Text Summarizer. RNN 6. Chatbot Using Deep Learning ( Training/Generative) 7. Colouring old B&W photos (Deep Neural Networks OpenCV) 8. Animal detection by training from multiple classes (CNN) 9. Face detection
Read more

8. Advanced CNN (Build AlexNet using Advanced CNN)

  Building and training an AlexNet-like model using the CIFAR-10 dataset in TensorFlow/Keras: Program to build the model: import tensorflow as tf from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout from tensorflow.keras.datasets import cifar10 from tensorflow.keras.utils import to_categorical from sklearn.model_selection import train_test_split # Load and preprocess CIFAR-10 dataset (x_train, y_train), (x_test, y_test) = cifar10.load_data() x_train = x_train.astype( 'float32' ) / 255.0 x_test = x_test.astype( 'float32' ) / 255.0 y_train = to_categorical(y_train, num_classes= 10 ) y_test = to_categorical(y_test, num_classes= 10 ) # Split into training and validation sets x_train, x_val, y_train, y_val = train_test_split(x_train, y_train, test_size= 0.1 , random_state= 42 ) # Define the model architecture '''model = tf.keras.Sequential([     Conv2D(96, (11, 11), strides=(4, 4), activation='relu', input_shape=(32...
Read more