Advanced Deep Learning using Python

This 3 month program offers the student an advanced perspective to deep learning applications. Enroll in the program to kickstart your career in deep learning!

  • Domain : CSE
Enroll Now View demo

A Quick Overview

Most people conjure an imaginative image of a robot when we speak the words Machine Learning and Deep Learning. Of Course  these two are advanced topics even for a computer science engineering student. So, what exactly are machine learning and deep learning? You see, Machine learning when at its most basic is a procedure of using algorithms to interpret data, learn from it and make a determination or prediction about something. So, instead of manually coding softwares routines which have a specific set of instructions to go ahead and accomplish a certain task, the machine is trained to do the task. Large amounts of data is used to train the machine to do our bidding, the algorithms also give it the ability to learn the task and how to perform it. Over the years the algorithmic approach included techniques like decision tree learning, inductive logic programming, clustering, reinforcement learning etc.

One of the very best application areas for machine learning for many years was computer vision. Although the early computer vision programs had great potential, they still required a lot of work to be done on them. There’s a reason why computer vision and image detection didn't come close to rivalling humans until very recently, it was too prone to error. Time and the right learning techniques made all the difference. One of the techniques is deep learning. Deep learning has enabled many practical applications of machine learning. It breaks down tasks in ways that make all kinds of machine assistance possible. Ranging from autonomous cars and all the way to movie recommendations. With the ever pacing research and development that is being done in AI, who knows, in a few years time, you might even have your own C3PO that’ll take care of you. 


Get a 1-on-1 demo to understand what is included in the course and how it can benefit you from an experienced sales consultant. The demo session will help you enroll in this course with a clear vision and confidence.

Request a Demo Session


1Artificial Neural Network (Feed Forward Neural Network)

The introductory week will look into forward feed neural networks. The feedforward neural network was the first and simplest type of artificial neural network devised. In this network, the information moves in only one direction forward-from the input nodes, through the hidden nodes (if any) and to the output nodes. There are no cycles or loops in the network. We will also look into -

  • Neural Network
  • Different architecture of Neural Network
  • Importance of Neural Network
  • Hyperparameters in Neural Network
  • Different types of Gradient descent methods

2Activation functions in neural networks

In the second week, we will look into activation functions. Activation functions are mathematical equations that are used to determine the output of a neural network. The function is attached to each neuron in the network, and is used to determine whether it should be activated or not, based on whether each neuron's input is relevant for the model's prediction. In activation functions, we will look into- 

  • Conic sections
  • Hyperbolic trigonometric functions
  • Sigmoid activation function
  • Tanhx activation function
  • Relu activation function
  • Softmax activation function

3Deep Learning

Deep learning is a branch of machine learning which is based on artificial neural networks. A neural network is a mimic of the human brain, so in short deep learning is also a mimic of human learning techniques. In deep learning, the software engineer doesnt program everything, instead we focus on developing our neural network. In this week, we will be looking into-

  • Terminologies in deep learning
  • Nomenclature
  • Order of vectorized forms
  • Forward propagation derivation with 1 layer
  • Back propagation derivation with 1 layer
  • Batch size, Iteration and Epoch

4Evaluation of models

The performance of a machine learning model can be characterized in terms of the bias and the variance of the model. A model with high bias makes strong assumptions about the form of the unknown underlying function that maps inputs to outputs in the dataset, such as linear regression. A model with high variance is highly dependent upon the specifics of the training dataset, such as unpruned decision trees. So, what are bias and variance?- Bias is the simplifying assumptions made by the model to make the target function easier to approximate and variance is the amount that the estimate of the target function will change given different training data. So, in this week we will look into different topics related to evaluation of models-

  • Underfitting
  • Overfitting
  • Lasso regularization
  • Ridge regularization
  • Elastic Net regularization

5Improvise the model

Ensemble methods are meta-algorithms that combine several machine learning techniques into one predictive model in order to decrease variance, bias, or improve predictions.

  • Sparse and convex functions
  • Bagging to avoid overfitting
  • Boosting to avoid underfitting
  • Stacking to avoid underfitting


Regularization is a set of techniques that can prevent overfitting in neural networks and thus improve the accuracy of a Deep Learning model when facing completely new data from the problem domain. And Optimizers are algorithms or methods used to change the attributes of your neural network such as weights and learning rate in order to reduce the losses. In this week we will look into the different types of regularisers and optimisers- 

  • Frobenius norm regularization
  • Data augmentation
  • Early stopping
  • Adam optimizer
  • Tensorflow 2.0


In deep learning, a convolutional neural network is a class of deep neural networks, most commonly applied to analyzing visual imagery. In this week we will look into more topics related to CNN such as-

  • Basics of CNN
  • Edge detection
  • Padding
  • Stride
  • Simple CNN
  • Difference between CNN & ANN


This week is a continuation of the previous week’s topic. Here we will look into more topics related to CNN.

  • Pooling layers
  • Transfer learning
  • Examples on CNN architecture
  • Combination of different Neural network architecture
  • CNN in python


A recurrent neural network (RNN) is a class of artificial neural networks where connections between nodes form a directed graph along a temporal sequence. This allows it to exhibit temporal dynamic behavior. Derived from feedforward neural networks, RNNs can use their internal state (memory) to process variable length sequences of inputs. This makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.

  • RNN Model
  • Different types of RNN
  • Gradients in RNN
  • Back propagation
  • Difference between RNN & ANN


This week is a continuation of the previous week’s topic. Here we will look into more topics related to RNN.

  • Gated Recurrent Unit (RNN)
  • Long short term memory (LSTM)
  • Bidirectional RNN
  • RNN Implementation in Python

11Basics of NLP

Natural Language Processing(NLP) refers to computer systems designed to understand human language. Human language, like English or Hindi consists of words and sentences, and NLP attempts to extract information from these sentences. Word embedding is any of a set of language modeling and feature learning techniques in natural language processing where words or phrases from the vocabulary are mapped to vectors of real numbers.

  • Stop words
  • Stemming
  • Lemmatization
  • Word2vec
  • Implementation of word2vec in python

12End-to-End ML Project steps

In this week, we will be performing an end-to-end ML/DL project for machine failure.

  • Descriptive Analytics
  • Diagnostic Analytics
  • Predictive Analytics
  • Prescriptive Analytics

Projects Overview

Project 1


Perform 3 Gradient Descent on the given dataset using python

  1. Batch Gradient Descent with all data points (Plot loss v/s iteration)
  2. Minibatch Gradient descent with batch size=100 (Plot loss v/s epoch)
  3. Stochastic Gradient descent with batch size=1 (Plot loss v/s epoch)

Project 2


Write the steps of gradient descent for logistic regression with output having 3 classes and 2 input features, n samples on paper/word document

Project 3


Perform gradient descent for the small dataset which has 3 input features, 1 binary output. Consider the hidden layer with 4 units with activation function as sigmoid on python/paper

Project 4


Perform Linear Regression & check for bias/variance and try avoiding it

Project 5


Identify the working principle of all 5 Gradient boosting method & list down its advantage & disadvantage

Project 6


Prediction of machine failure for the given dataset using ANN (Hyperparameters is completely dependent on individuals to come up with the best model)

Project 7


Identify the formula behind output dimension in terms of both padding and stride

Project 8


Identify the dataset from opensource which has binary classification on images and perform CNN (or) Perform CNN on the given dataset which has 17 classes on different vehicles

Project 9


Explain vanishing gradient problem in RNN

Project 10


Perform RNN/LSTM/GRU/Bi-directional on spam filtering dataset

Project 11


Perform either Machine Learning or Deep Learning algorithm on Credit card fraud detection dataset (Its completely up to student which algorithm/strategy they want to apply on this dataset)


  • For students of Mechanical Engineering



This course covers basic knowledge of Python and involves ML algorithms in Python. Python is very famous software and can be used in various domains. In recent times, python has gained lot of popularity due to machine learning and deep learning. Python is quite robust for both machine learning and deep learning. Another popular software “R” can be used for Statistics and machine learning but in this course we will be learning python as it can utilized in various domains. Many organizations also uses python for their framework.

Flexible Course Fees

Choose the plan that’s right for you


2 Months Access


Per month for 3 months

  • Access Duration : 2 months
  • Mode of Delivery : Online
  • Project Portfolio : Available
  • Certification : Available
  • Email Support : Available
  • Forum Support : Available

Lifetime Access


Per month for 3 months

  • Access Duration : Lifetime
  • Mode of Delivery : Online
  • Project Portfolio : Available
  • Certification : Available
  • Individual Video Support : 12/month
  • Group Video Support : 12/month
  • Email Support : 12/month
  • Forum Support : Available
  • Telephone Support : Available
  • Dedicated Support Engineer : Available

You Might Also Be Interested In

Related Courses

See all


  • Top 5% of the class will get a merit certificate
  • Course completion certificates will be provided to all students
  • Build a professional portfolio
  • Automatically link your technical projects
  • E-verified profile that can be shared on LinkedIn

Frequently Asked Questions

1Who can take this course?

Any student from any domain who is willing to get into industry

2What is included in your course?

a) Advance machine learning which is in continuation of course 1 & 2

b) Artificial, Convolutional and Recurrent Neural Network

3What will the student gain from your course?

a) Hands on experience on python with Tensorflow2.0
b) Implementation of machine learning on unstructured data as machine learning techniques for structured data is already covered in course 1 & 2

4What software skills are you teaching and how well are these tools used in the industry?

Python is one of the leading software’s for any applications in India and abroad. In particular to machine learning, more than 80 % of the industries required candidates with python competency

5What is the real world application for the tools and techniques will you teach in this course?

Autonomous driving, Speech recognition, Facebook photo tagging, Filtering emails, Predicting words while writing sentences, predicting attrition rate, predicting thermal conditions of the components, Recommendations in amazon and flipkart etc

6Which companies use these techniques and for what?

Some of the high-profile companies in mechanical industry which uses these techniques are Mercedes Benz, Lam Research, Renault & Nissan, Faurecia, Hyundai, Rolls Royce etc. Important to mention that more than 90 % of the companies uses machine learning/ artificial intelligence in current era

7How is your course going to help me in my path to MS or PhD?

Course1,2 and 3 all inclusive can be considered itself as one big certification but if someone wants to pursue Masters/ PhD then this course will be highly useful as this course takes python into consideration and the future technologies. The projects in the course1,2 and 3 are designed in a way that helps students to apply for higher education or for a job

8How is this course going to help me get a job?

There are many opportunities in India and abroad with respect to Machine learning/ Deep learning and this course is made focusing on the parameters which are required in cracking a Data science interview. This course can land student in either a Data Analyst or Data Scientist job.

The Skill-Lync Advantage

See all


Companies hire from us

See all


See all