Deep Learning with Tensorflow

Application fee : 400 INR

Details

Location: On-campus (India, Mumbai, Pune, Bangalore)
Type: Certificate course
Language: English
Course fee: 25000 INR
Rating:
No Ratings

Gallery

Course Details

Aegis School of Data Science & Telecommunication and NVIDIA announced a strategic partnership at the Data Science Congress to conduct imparting training on Artificial Intelligence (AI) for Corporates and Individuals. The purpose of this partnership is to build a large pool of skilled manpower in the Deep Learning space to fill the skill gaps. This initiative will feature several courses for DL, ML and AI, facilitated by Aegis School of Data Science and powered by NVIDIA Deep Learning Institute. The students will also be given access to NVIDIA’s proprietary technologies, software, labs, subject matter experts, engineers, and data scientists. This will help them develop skills for the future as well as today’s industry requirement.

nvidia-aegis-mou-signing-ceremony-600x

What is Deep learning?

Deep learning (also known as deep structured learning, hierarchical learning or deep machine learning) is the study of artificial neural networks that contain more than one hidden layer. It is part of a broader family of machine learning methods based on learning representations of data. An observation (e.g., an image) can be represented in many ways such as a vector of intensity values per pixel, or in a more abstract way as a set of edges, regions of particular shape, etc. 

Thanks to the era of NVIDIA’s GPU computing, training deep neural networks is more efficient than ever in terms of both time and resource cost. The result is an AI boom that has given machines the ability to perceive — and understand — the world around us in ways that mimic, and even surpass, our own.

Deep learning is part of a broader family of machine learning methods based on learning representations of data. An observation can be represented in many ways such as a vector of intensity values per pixel, or in a more abstract way as a set of edges, regions of particular shape, etc. Some representations are better than others at simplifying the learning task e.g. face recognition or facial expression recognition. One of the promises of deep learning is replacing handcrafted features with efficient algorithms for unsupervised or semi-supervised feature learning and hierarchical feature extraction.

Research in this area attempts to make better representations and create models to learn these representations from large-scale unlabeled data. Some of the representations are inspired by advances in neuroscience and are loosely based on interpretation of information processing and communication patterns in a nervous system, such as neural coding which attempts to define a relationship between various stimuli and associated neuronal responses in the brain.

Various deep learning architectures such as deep neural networks, convolutional deep neural networks, deep belief networks and recurrent neural networks have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks.

TensorFlow

TensorFlow is an open source deep learning library developed by researchers and engineers working on the Google Brain Team within Google's Machine Intelligence research organization for the purposes of conducting machine learning and deep learning research.

TensorFlow is comprised of numerical computation using data flow graphs, wherein nodes represent mathematical operations, while the graph edges represent the multidimensional data arrays (tensors) communicated between them. The flexible architecture of tensorflow makes the deployment of the machine learning and deep learning models easier in a desktop, server, or mobile device.

                                                      

Course details

Difficulty level: Intermediate

Pre-requisites:

  • Machine Learning (Intermediate level)
  • Python programming (Beginner level)

Hardware and OS requirements:

  • 40 GB free disk space
  • 4 GB RAM (8 GB preferred)
  • Any recent Intel processor
  • Any recent NVIDIA GPU (preferred)
  • Windows 7 (64-bit) Operating System or later
  • High speed Internet connectivity

Software requirement: Any browser application IE or Chrome or Firefox

Objective: To help participants, for solving real world problems by using Deep Learning concepts

Agenda:

  • Introduction to Neural Networks
  • Forward and backward propagation
  • Introduction to Deep Learning
  • Convolution Neural Network
  • Recurrent Neural Network
  • Tools : Tensorflow, Keras
  • Applications : Face Recognition, Face Emotion Detection, Object Detection, Image Segmentation, Text Classification, Sentiment Analysis, etc