Advanced Deep Learning using Python in Bangalore
Gain an in-depth understanding about deep learning algorithms and their development using Python.
RELATED RECENT PLACEMENTS
Rohit Mali
William O'Neil India
NMIMS MUMBAI
Dhiraj Satghare
RD Civil Solution
Acharya Shrimannarayan Polytechnic
Namrata Rao
Piaggio & C. S.p.A.
Rajeev Gandhi College of Engg and Research Institute
Siddhi Parab
C.C Engineers
lokmanya tilak college of engineering
Anil Katarkar
3D engineering
NATIONAL INSTITUTE OF TECHNOLOGY
Bhavesh Kumbhare
Dar Al-Handasah Engineering company
Rashtrasant Tukadoji Maharaj Nagpur University
Akash Bhadkumbe
XS CAD
Dr. D Y Patil College of Engineering & Innovation, Varale
Madhura Joshi
NEILSOFT LIMITED
Government Polytechnic Ratnagiri
Syllabus
This course is full of best-in-class content by leading faculty and industry experts in the form of videos and projects
Course Overview
Automating machines to process information and replicate knowledge-levels like humans is the primary focus of deep learning and neural networks. Deep learning simplifies the process of gathering, assessing, and interpreting data sets for engineers, and offers a proactive solution to foreseeing events by studying patterns. Engineers can develop and study versatile deep learning codes using Python - making it a fundamental skill in the job industry.
This course is focused on enriching engineers with theoretical and practical knowledge on the following:
- Feed forward neural networks
- Activation functions
- Deep learning algorithms
- Convolutional neural networks
- Recurrent neural networks
- Natural language processing
You will also get to complete projects requiring extensive hands-on work with Python according to modern trends in the industry.
Course Syllabus in Bangalore
On a daily basis we talk to companies in the likes of Tata Elxsi and Mahindra to fine tune our curriculum.
Week 1 - Artificial Neural Network (Feed Forward Neural Network)
This week will cover
- Neural networks
- Different architectures of Neural Networks
- Importance of Neural Networks
- Hyperparameters in Neural Networks
- Different types of Gradient descent methods
Week 2 - Activation Functions in Neural Networks
This week will cover
- Conic sections
- Hyperbolic trigonometric functions
- Sigmoid activation function
- Tanhx activation function
- Relu activation function
- Softmax activation function
Week 3 - Deep Learning
This week will cover
- Deep learning terminologies
- Nomenclature
- Order of vectorized forms
- Forward propagation derivation with 1 layer
- Back propagation derivation with 1 layer
- Batch size, iteration and epoch
Week 4 - Evaluation of Models
This week will cover
- Underfitting
- Overfitting
- Lasso regularization
- Ridge regularization
- Elastic Net regularization
Week 5 - Improvising the Model
This week will cover
- Ensemble methods
- Sparse and convex functions
- Bagging to avoid overfitting
- Boosting to avoid underfitting
- Stacking to avoid underfitting
Week 6 - Optimizers
This week will cover
- Frobenius norm regularization
- Data augmentation
- Early stopping
- Adam optimizer
- Tensorflow 2.0
Week 7 - Convolutional Neural Network (CNN) - Part 1
This week will cover
- Basics of CNN
- Edge detection
- Padding
- Stride
- Simple CNN
- Difference between CNN & ANN
Week 8 - Convolutional Neural Network (CNN)- Part 2
This week will cover
- Pooling layers
- Transfer learning
- Examples of CNN architecture
- Combination of different Neural network architecture
- CNN in Python
Week 9 - Recurrent Neural Network (RNN) - Part 1
This week will cover
- RNN Model
- Different types of RNN
- Gradients in RNN
- Back propagation
- Difference between RNN & ANN
Week 10 - Recurrent Neural Network (RNN) - Part 2
This week will cover
- Gated Recurrent Unit (RNN)
- Long short term memory (LSTM)
- Bidirectional RNN
- RNN Implementation in Python
Week 11 - Basics of Natural Language Processing (NLP)
This week will cover
- Stop words
- Stemming
- Lemmatization
- Word2vec
- Implementation of word2vec in Python
Week 12 - End-to-End ML Project Steps
This week will cover
- Descriptive Analytics
- Diagnostic Analytics
- Predictive Analytics
- Prescriptive Analytics
Our courses have been designed by industry experts to help students achieve their dream careers
Industry Projects in Bangalore
Our projects are designed by experts in the industry to reflect industry standards. By working through our projects, Learners will gain a practical understanding of what they will take on at a larger-scale in the industry. In total, there are 2 Projects that are available in this program.
Logistic Regression and Gradient Descent
In this project, you will perform logistic regression and gradient descent on a given dataset using Python.
ANN, CNN and RNN
In this project, you will have to work on prediction of machine failure for a given dataset using ANN (Hyperparameters is completely dependent on individuals to come up with the best model).
Our courses have been designed by industry experts to help students achieve their dream careers
Ratings & Reviews by Learners
Skill-Lync has received honest feedback from our learners around the globe.
Instructors profiles
Our courses are designed by leading academicians and experienced industry professionals.
1 industry expert
Our instructors are industry experts along with a passion to teach.
8 years in the experience range
Instructors with 8 years extensive industry experience.
Areas of expertise
- Machine Learning
- Deep Learning
Find Advanced Deep Learning using Python in other cities
Pune
Delhi
Hyderabad
Mumbai
Chennai
Similar Courses
Got more questions?
Talk to our Team Directly
Please fill in your number & an expert from our team will call you shortly.