9923170071 / 8108094992 info@dimensionless.in

Deep Learning

Deep learning is a branch of Machine Learning algorithms which deals with empowering machine to take decisions like humans using Artificial Neural Network. This in-depth course provides you with all the tools and techniques to get started with deep learning, and how to use neural networks to address some of the common machine learning problems.


  • Learn the basics of Artificial Neural Networks with Keras
  • Start Training Deep Neural Networks
  • Custom Models and Training with TensorFlow
  • Deep Computer Vision Using Convolutional Neural Networks
  • Model Planning, Data Modelling and Model Evaluation using real time case studies


  • Instructor led online LIVE session for entire course duration
  • Small batch size– Personalized attention
  • Highly Interactive sessions (Two way participation – Chat and Speech)
  • Highly experience and Qualified Trainers [Analytics experts, 10+ years industry experience (IITians)
  • 20+ hours of In-depth case study discussion – Multiple domain Specific Projects
  • Lifetime Access to Session Recordings & Case studies through Learning Manangement Portal
  • Course Completion Certification
  • Highly approachable faculty – 24*7 support available
  • Reattend LIVE sessions -If you miss a Lecture due to some reason



60+ hours


Weekends – 6 hours
9.30 PM IST to 12.00 PM IST


Introduction to Artificial Neural Networks with Keras

From Biological to Artificial Neurons
●  The Perceptron
●  Optimizer – Gradient Descent, Mini Batch Gradient Descent, Stochastic Gradient
●  Loss Functions – MSE, Cross Entropy,Softmax
●  Multi-Layer Perceptron and Backpropagation
●  Regression MLPs
●  Classification MLPs
●  Implementing MLPs with Keras
●  Installing TensorFlow 2
●  Building an Image Classifier Using the Sequential API
●  Building a Regression MLP Using the Sequential API
●  Building Complex Models Using the Functional API
●  Building Dynamic Models Using the Subclassing API
●  Saving and Restoring a Model
●  Using Callbacks
●  Visualization Using TensorBoard
●  Fine-Tuning Neural Network Hyperparameters
●  Number of Hidden Layers
●  Number of Neurons per Hidden Layer
●  Learning Rate, Batch Size and Other Hyperparameters

Training Deep Neural Networks

● Vanishing/Exploding Gradients Problems
● Glorot and He Initialization
● Non-Saturating Activation Functions
● Batch Normalization
● Gradient Clipping
● Reusing Pretrained Layers
● Transfer Learning With Keras

● Faster Optimizers
● Momentum Optimization
● Nesterov Accelerated Gradient
● AdaGrad
● RMSProp
● Adam and Nadam Optimization
● Learning Rate Scheduling
● Avoiding Overfitting Through Regularization
● l1 and l2 Regularization
● Dropout
● Monte-Carlo (MC) Dropout
● Max-Norm Regularization
● Summary and Practical Guidelines

Custom Models and Training with TensorFlow

● Introduction to TensorFlow
● Using TensorFlow like NumPy
● Tensors and Operations
● Tensors and NumPy
● Type Conversions
● Variables
● Other Data Structures
● Customizing Models and Training Algorithms
● Custom Loss Functions
● Saving and Loading Models That Contain Custom Components
● Custom Activation Functions, Initializers, Regularizers, and Constraints
● Custom Metrics
● Custom Layers
● Custom Models
● Losses and Metrics Based on Model Internals
● Computing Gradients Using Autodiff
● Custom Training Loops
● TensorFlow Functions and Graphs
● Autograph and Tracing
● TF Function Rules
● Loading and Preprocessing Data with TensorFlow
● The Data API
● The Features API

Deep Computer Vision Using Convolutional Neural Networks

● Convolutional Layer
● Filters

● Stacking Multiple Feature Maps
● TensorFlow Implementation
● Memory Requirements
● Pooling Layer
● TensorFlow Implementation
● CNN Architectures
● LeNet-5
● AlexNet
● GoogLeNet
● VGGNet
● ResNet
● Xception
● SENet
● Implementing a ResNet-34 CNN Using Keras
● Using Pre-Trained Models From Keras
● Pretrained Models for Transfer Learning
● Classification and Localization
● Object Detection
● Fully Convolutional Networks (FCNs)
● You Only Look Once (YOLO)


  • Online Classes [Get the services of best trainers from Anywhere]
  • LIVE instructor-led training throughout the training duration
  • Entirely Hands-On driven session
  • Practical Inputs from real-time scenarios
  • Problems and Case Study driven training
  • Machine Learning algorithms are taught using at least 2 Case Studies for every algorithm


Kushagra, (IIT Delhi – 10+ years experience in Analytics & data science), has a keen interest in Problem Solving, Deriving insights & Improving the efficiency of processes with new age technologies.

He’s good with statistical concepts and possess thorough business understanding along with practical experience in linear models (like Linear Regression, Logistic Regression, Ridge Regression, Lasso Regression),

Tree based algorithms (like Decision trees, Bagging, Random Forest, GBM, XGBoost), clustering (like K-Means, Hierarchical),Time-series analysis (like ARMA, ARIMA, stationarity), Deep learning(CN, RNN), NLP Techniques(TFIDF, LDA, Topic Modelling) Extensive knowledge of Tools like R,Python, Spark, Tensorflow, Keras, Tableau. Trained 5000+ participants in R, Machine Learning, Tableau and Python, Big Data Analytics at Dimensionless Conducted workshops and training on Data Analytics for Corporate and Colleges

Read More

HIMANSHU (IIT, Bombay – 10+ years experience in Data Science) A machine-learning practitioner, fascinated by the numerous application of Artificial Intelligence in the day to day life.

I enjoy applying my quantitative skills to new large-scale, data-intensive problems. I am an avid learner keen to be the frontrunner in the field of AI. I enjoy learning new technologies at work and strive hard to acquire finesse in skills that I have honed over my career.

Trained 5000+ participants in R, Machine Learning, Tableau and Python, Big Data Analytics and Deep Learning at Dimensionless

Conducted workshops and training on Data Analytics for Corporate and Colleges

He possesses knowledge of a wide variety of machine learning and deep learning algorithms.

Read More

Pranali is a professional Data Science Trainer with more than 15 years of experience in the teaching various training programs on Databases, Programing and Machine Learning.
Her core competency include Databases, Data Science and Big Data. She holds a Masters degree in Computer Engineering from University of Pune.


Are there any pre-requisites to learn this course?

  • Yes, the participant should have a working knowledge of Python for Data Science and must have worked on Machine Learning Algorithms.

Why Should I Learn Data Science from Dimensionless?

  • Dimensionless Tech provides best online data science training that provides in-depth course coverage, case study based learning, entirely Hands-on driven sessions with Personalised attention for every participant. We guarantee Learning.

What Are The Various Modes Of Training That you Offer?

  • We provide only instructor led LIVE online training sessions. We do not provide classroom trainings.

How is your online training better than other online or classroom training?

  • In physical classrooms, students generally feel hesitant to ask questions. Unlike other online courses,  we allow you to speak in the session and clarify your doubts. The interactivity level is similar to classroom training and you get it in the comfort of your home. If you miss any class or didn’t understand some concepts, you can’t go through the class again. However, in online courses, it’s possible to do that. We share the recordings of all our classes after each class with the student. Also, there’s no hassle of long distance commuting and disrupting your schedule.

Can I ask my doubts during the session?

  • All participants are encouraged to speak up and ask their doubts. We answer all the doubts with the same sincerity.

Where do I get the Softwares from?

  • All the software used in this course are Freely downloadable from the Internet. The trainers help you set it up in your systems. We also provide access to our Cloud-based online lab where these are already installed.

What is the hardware requirement for this course?

  • Any laptop with 2GB RAM and Windows 7 and above is perfectly fine for this course. For large data, the access will be given on the online lab. 

What if I miss a session, due to some unavoidable situation?

  • We understand that while balancing your personal and professional commitments you might miss a session. Hence, all our sessions are recorded and the recordings are shared with you through our Learning Management Portal.

How long will I have access to the Learning Management Portal?

  • You will have lifetime access to the portal and you can view the Videos, Notes, Books, Assignments as many time

What Kind Of Projects Will I Be Working On As Part Of The Training?

  • During the training you will be solving multiple case studies from different domains. Once the LIVE training is done, you will start implementing your learnings on Real Time Datasets.  You can work on data from various domains like Retail, Manufacturing, Supply Chain, Operations, Telecom, Oil and Gas and many more. You would be working on multiple projects so that you can gain enough content and confidence to enter into the field of Data Science.

Do You Provide Placement Assistance?

  • Yes, we provide you with real-time industry requirements on a daily basis through our connection in the industry. These requirements generally come through referral channels, hence the probability to get through increases manifold.

    The HR from the team helps you with Resume Building and Interview Preparation as well.

Do I get a Course Completion Certificate?

  • Yes, we will be issuing a course completion certification to all individuals who successfully complete the training.


Fake news refers to propaganda, misinformation which is spread via word of mouth, or mainstream media or social media platform.

The goal is to create a model which characterizes fake news and real news with the help of NLP and deep learning techniques.

In this project, we will compose our own original music without really knowing any instruments or music by using Deep Learning.

You will be provided with existing music data and your task is to make a deep learning model that generates new music.

Image Processing: The dataset given to you contains high-quality photoshopped face images.

Your task is to make a Deep Learning model that detects whether the face is a real face or a fake face that is either photoshopped or created by AI.

Your task is to make a model that answers open-ended questions about images using deep learning techniques.

This project can also be upscaled by adding voice features that can help visually impaired people to get a gist of their surroundings.

Signature authentication is necessary to avoid forgery of documents in various financial, legal, business and in other environments.

The aim of is to develop a signature verification system that detects whether the signature is fraud or genuine.


MNIST Digit Recognition

MNIST digit is a dataset of 60,000 small square 28×28 pixels. It is classified into the 10 classes using the ANN.

Fashion MNIST

The fashion-MNIST dataset consists of the images of fashion articles that are classified into their classes.

Movie Reviews Sentiment Analysis

Analyze a dataset of 25,000 movie reviews from the website IMDB, labeled by sentiment (positive or negative).

Image Recognition on CIFAR-10

The CIFAR-10 dataset consists of 60000 32×32 colour images.The dataset is used for computer vision algorithms.

Image Classification on Flowers Dataset

CNN is used to classify the flower images in respective class: daisy, tulip, rose, sunflower and dandelion.

Cats and Dogs classification

The task is to classify cats and dogs with the help of CNN from 50000 images data set of cats and dogs.

Cards Recognition and Detection

The dataset consists of different images from a deck. Goal is to identify the card and detect the image.