Deep Learning – Master Data Science

#011 Deep L-layer Neural Network

How deep representation of a Neural Network looks like?

#012A Building a Deep Neural Network

What are the building blocks of a Deep Neural Network?

#012B Building a Deep Neural Network from scratch in Python

How to implement a deep Neural Network in Python from scratch?

#001 CNN Convolutional Neural Networks

Introduction to Computer Vision

#002 CNN Edge detection

How can we discover the edges in the picture?

#003 CNN More On Edge Detection

How to choose the proper weights for your filter?

#004 CNN Padding

Applying padding of 1 before convolving with filter

How do we decide the values for padding?

#005 CNN Strided Convolution

How to define the step size of the kernel when traversing the image?

#006 CNN Convolution On RGB Images

How to apply strides in volume on Convolutional Neural Network?

#007 CNN One Layer of A ConvNet

How to calculate the number of parameters in Convolutional Neural Networks?

#008 CNN An Example of A Convolutional Neural Network

Learn to build your first simple Convolutional Neural Network

#009 CNN Pooling Layers

The most common methods of speeding up ConvNets

#010 CNN An Example of a Neural Network

An example of Neural Network with fully connected layers

#011 CNN Why convolutions ?

How do we know when to use a Convolutional Neural Network?

#012 CNN Convolutional Neural Networks – An Overview

An overview of the 11 Convolutional Neural Network architectures

#013A CNN LeNet-5

The goal of LeNet−5 is to recognize handwritten digits. This is how the architecture af a LeNet-5 looks like?

#013B CNN AlexNet

How does the architecture of an AlexNet looks like?

#013C CNN VGG Neural Network (VGG 16 and VGG 19)

How does a VGG Neural Network architecture looks like ?

#014 CNN Residual nets

How does a ResNet architecture looks like ?

#015 CNN Why ResNets work ?

A big neural network with a skipped connection

An example that illustrates why ResNets work so well

#016 CNN Network in Network – 1×1 Convolutions

An example of a 1×1 convolutions on a 3D images

An example of how we can reduce a number of channels witx 1×1 convolution

#017 CNN Inception Network

Introduction to basic building blocks of the Inception Network.

#018 CNN Inception Network – Inception Module

How to put basic building blocks together and build the Inception Network?

#019 CNN Transfer Learning

Three possible classes of a neural network

How to solve a problem of complex Neural Network architectures?

#020 CNN Data Augmentation

Data augmentation is one of the techniques that is used to improve the performance of computer vision systems

#021 CNN Object Localization

Object localization, classification and detection

In order to build up object detection we first need to learn about object localization

#022 CNN Landmark Detection

How we can get a Neural Network to output specific bounding boxes of an object?

#023 CNN Object Detection

How we can build an object detection algorithm using Convolutional Neural Network?

#024 CNN Convolutional Operation of Sliding Windows

Turning Fully connected layers into Convolutional layers

Learn how to implement sliding windows convolutionally?

#025 CNN Bounding Box Predictions

How to obtain more accurate predictions of bounding boxes?

#026 CNN Intersection over Union

Learn about a function called Intersection over union. We will use this function to make the object detection algorithm work even better

#027 CNN Non-Max Suppression algorithm

How to overcome multiple detection of the same object?

#028 CNN Anchor Boxes

How to overcome multiple detection of the same object using the idea of Anchorboxes ?

#029 CNN Yolo Algorithm

How to create the Yolo object detection algorithm?

#030 CNN One-Shot Learning

How to recognize a person given just one example?

# 031 CNN Siamese Network

How to use two faces that will tell us how similar or how different they are?

#032 CNN Triplet Loss

How to define an objective function to make our Neural Network learn?

#001 RNN – Recurrent Neural Networks

The fundamental theory of Recurrent Neural Networks, the motivation for its use, and basic notation

#002 RNN – Architecture, Mapping, and Propagation

Learn how to build and represent basic RNN models using the mathematical notations of Forward and Back Propagation techniques

#003 RNN – Architectural Types of Different Recurrent Neural Networks

Start to explore the various categories of RNNs and learn how these different models solve day to day problems

#004 RNN - Language Modelling and Sampling Novel Sequences

Learn how RNNs are used to build and train Language Models and sample novel sequences from trained models

# 005 RNN – Tackling Vanishing Gradients with GRU and LSTM

Learn how you can solve Vanishing Gradient problems by modifying your basic RNN architecture