Deep Learning is one of the fastest growing technologies in recent years. Deep Learning also known as hierarchical Learning, is a sub field of Machine Learning methods based on Artificial Neural Networks and is inspired by the structure and function of the brain. You can compare it to the way human beings take in information and learns something, only here it is a computer that is fed with huge amounts of data and learns by itself from this data.
Deep Learning can be supervised, semi supervised, unsupervised and reinforcement learning.
Deep learning architectures such as deep neural networks (DNN), recurrent neural networks (RNN) and convolutional neural networks(CNN) are the key technologies behind computer vision,Image recognition, driverless cars, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, bioinformatics, drug design, medical image analysis, material inspection and board game programs, where they have produced results that have exceeded human expectations or comparable to and in some cases superior to human experts.Models are trained by using a large set of labeled data and neural network architectures that contain many layers.
Think of Deep Learning as large deep neural net with n number of hidden layers. Accuracy of the neural network gets better with more data, more layers and more computation power.
Few applications of Deep Learning are
1) Virtual Assistant or Automatic Voice Recognition- Apple Siri, Microsoft Cortana, Amazon Alexa, Google Now etc
2) Translation – Skype Translator, Google Translate etc
3) Computer Vision – Image Recognition, Facial Recognition
4) Natural Language Processing
5) Drug Discovery & Toxicology
6) Recommendation Engine
8) Medical Image Analysis
9) Image Restoration
10) Financial Fraud Detection
High Points of Deep Learning Training
1) To install and use Python and Keras to build deep learning models
2) Keras is one of the most popular deep learning frameworks for beginners and can build very complex deep learning models very quickly.
3) To apply deep learning to solve supervised and unsupervised learning problems involving images, text, sound, time series and tabular data.
4) To build, train and use fully connected, convolutional and recurrent neural networks
5) Convolutional Neural Networks with Keras for image classification
6) To train and run models in the cloud using a GPU
Prerequisite of Deep Learning Training
1) Knowledge of Python, familiarity with control flow (if/else, for loops) and pythonic constructs (functions, classes, iterables, generators)
2) Prior knowledge of Machine Learning
|Deep Learning With Kera & Tensorflow|
|Introduction Deep Learning||00:00:00|
|Understanding Artificial Neural Networks – ANN||00:00:00|
|Neural Network & Regression Models||00:00:00|
|How Neural Network Works||00:00:00|
|How Neural Network Learns||00:00:00|
|Multi-layer Neural Network||00:00:00|
|Optimising Neural Network||00:00:00|
|Calculating Model Error||00:00:00|
|Difference Between Keras & Tensorflow||00:00:00|
|Deep Learning With Keras|
|Understanding Keras Frame Work||00:00:00|
|Creating Keras Models||00:00:00|
|Keras – Neural Networks||00:00:00|
|Keras – Regression Model||00:00:00|
|Fine Tuning Models||00:00:00|
|Convolutional Neural Network|
|Introduction Convolutional Neural Network||00:00:00|
|Softmax And Cross Entropy||00:00:00|
|Cnn Case Study & Project||00:00:00|
No Reviews found for this course.