1628309939

In the fourth course of the Deep Learning Specialization, you will understand how computer vision has evolved and become familiar with its exciting applications such as autonomous driving, face recognition, reading radiology images, and more.

By the end, you will be able to build a convolutional neural network, including recent variations such as residual networks; apply convolutional networks to visual detection and recognition tasks; and use neural style transfer to generate art and apply these algorithms to a variety of image, video, and other 2D or 3D data.

The Deep Learning Specialization is our foundational program that will help you understand the capabilities, challenges, and consequences of deep learning and prepare you to participate in the development of leading-edge AI technology. It provides a pathway for you to gain the knowledge and skills to apply machine learning to your work, level up your technical career, and take the definitive step in the world of AI.

------------------ TIME STAMP ----------------

FOUNDATION OF CONVOLUTION NEURAL NETWORKS

0:00:00 Computer Vision

0:05:43 Edge Detection Example

0:17:14 More Edge Detection

0:25:11 Padding

0:35:01 Strided Convolutions

0:44:03 Convolutions Over Volume

0:54:48 One Layer of a Convolution Network

1:10:58 Simple Convolutional Network Example

1:19:30 Pooling Layers

1:29:55 CNN Example

1:42:32 Why Convolutions

1:52:12 Yann LeCun Interview

DEEP CONVOLUTION MODEL: CASE STUDIES

2:20:01 Why loot at case Studies

2:23:09 Classic Networks

2:41:28 ResNets

2:48:36 Why ResNets Work

2:57:48 Networks in Networks and 1X1 Convolutions

3:04:28 Inception Network Motivation

3:14:43 Inception Network

3:23:29 MobileNet

3:39:47 MobileNet Architecture

3:48:19 EfficientNet

3:51:59 Using Open-Source Implementation

3:56:56 Transfer Learning

4:05:44 Data Augmentation

4:15:15 State of Computer Vision

OBJECT DETECTION

4:27:53 Object Locallization

4:39:47 Landamark Detection

4:45:44 Object Detection

4:51:33 convolutional Implementation of Sliding Windows

5:02:41 Bounding Box Predictions

5:17:13 Intersection Over Union

5:21:32 Non-max Suppression

5:29:34 Anchor Boxes

5:39:17 YOLO Algorithm

5:46:18 Region Proposals (Optional)

5:52:45 Semantic Segmentation With U-Net

6:00:07 Transpose Convolutions

6:07:46 U-Net Architecture Intuition

6:11:08 U-Net Architecture

SPECIAL APPLICATIONS: FACE RECOGNITION & NEURAL STYLE TRANSFER

6:18:49 What is Face Recongnition

6:23:26 One shot Learning

6:28:11 Siamese Network

6:33:02 Triplet Loss

6:48:32 Face Verification and Binary Classification

6:54:38 What is Neural Style Transfer

6:56:40 What are deep ConNets Learning

7:04:38 Cost Function

7:08:37 content Cost function

7:12:15 Style Cost Function

7:25:32 ID and 3D Generalizations

⭐ Important Notes ⭐

⌨️ The creator of this course is Deeplearning.ai (Andrew Ng)

Note: If you have any copyright issue with the content used in our channel or you find something that belongs to you, before you claim it to Youtube, SEND US A MESSAGE and the respective content will be DELETED right away. Thanks for understanding.

#deep-learning #machine-learning

1597323120

CNN’s are a special type of ANN which accepts images as inputs. Below is the representation of a basic neuron of an ANN which takes as input X vector. The values in the X vector is then multiplied by corresponding weights to form a linear combination. To thus, a non-linearity function or an activation function is imposed so as to get the final output.

Neuron representation, Image by author

Talking about grayscale images, they have pixel ranges from 0 to 255 i.e. 8-bit pixel values. If the size of the image is NxM, then the size of the input vector will be N*M. For RGB images, it would be N*M*3. Consider an RGB image with size 30x30. This would require 2700 neurons. An RGB image of size 256x256 would require over 100000 neurons. ANN takes a vector of inputs and gives a product as a vector from another hidden layer that is fully connected to the input. The number of weights, parameters for 224x224x3 is very high. A single neuron in the output layer will have 224x224x3 weights coming into it. This would require more computation, memory, and data. CNN exploits the structure of images leading to a sparse connection between input and output neurons. Each layer performs convolution on CNN. CNN takes input as an image volume for the RGB image. Basically, an image is taken as an input and we apply kernel/filter on the image to get the output. CNN also enables parameter sharing between the output neurons which means that a feature detector (for example horizontal edge detector) that’s useful in one part of the image is probably useful in another part of the image.

Every output neuron is connected to a small neighborhood in the input through a weight matrix also referred to as a kernel or a weight matrix. We can define multiple kernels for every convolution layer each giving rise to an output. Each filter is moved around the input image giving rise to a 2nd output. The outputs corresponding to each filter are stacked giving rise to an output volume.

Convolution operation, Image by indoml

Here the matrix values are multiplied with corresponding values of kernel filter and then summation operation is performed to get the final output. The kernel filter slides over the input matrix in order to get the output vector. If the input matrix has dimensions of Nx and Ny, and the kernel matrix has dimensions of Fx and Fy, then the final output will have a dimension of Nx-Fx+1 and Ny-Fy+1. In CNN’s, weights represent a kernel filter. K kernel maps will provide k kernel features.

#artificial-neural-network #artificial-intelligence #convolutional-network #deep-learning #machine-learning #deep learning

1618317562

View more: https://www.inexture.com/services/deep-learning-development/

We at Inexture, strategically work on every project we are associated with. We propose a robust set of AI, ML, and DL consulting services. Our virtuoso team of data scientists and developers meticulously work on every project and add a personalized touch to it. Because we keep our clientele aware of everything being done associated with their project so there’s a sense of transparency being maintained. Leverage our services for your next AI project for end-to-end optimum services.

#deep learning development #deep learning framework #deep learning expert #deep learning ai #deep learning services

1597594620

*This post provides the details of the architecture of _Convolutional Neural Network _(CNN), functions and training of each layer, ending with a summary of the training of CNN.*

- The basic CNN architecture consists of:
**Input->(Conv+ReLU)->Pool->(Conv+ReLU)->Pool-> Flatten->Fully Connected->Softmax->Output** - The feature extraction is carried out in the Convolutional layer+ReLU and Pooling layers and the classification is carried out in Fully Connected and Softmax layers.

**3. First Convolutional Layer:**

- The primary purpose of this layer is to extract features from the input image.
- The
**convolution**is used to extract features because it preserves the spatial relationship between pixels by learning image features by using small squares of input data. - The convolutional layer have the following attributes:-

#convolutional-network #machine-learning #artificial-intelligence #deep-learning #neural-networks #deep learning

1593440910

**TL;DR** *This is the first in a [series of posts] where I will discuss the evolution and future trends in the field of deep learning on graphs.*

Deep learning on graphs, also known as Geometric deep learning (GDL) [1], Graph representation learning (GRL), or relational inductive biases [2], has recently become one of the hottest topics in machine learning. While early works on graph learning go back at least a decade [3] if not two [4], it is undoubtedly the past few years’ progress that has taken these methods from a niche into the spotlight of the ML community and even to the popular science press (with *Quanta Magazine* running a series of excellent articles on geometric deep learning for the study of manifolds, drug discovery, and protein science).

Graphs are powerful mathematical abstractions that can describe complex systems of relations and interactions in fields ranging from biology and high-energy physics to social science and economics. Since the amount of graph-structured data produced in some of these fields nowadays is enormous (prominent examples being social networks like Twitter and Facebook), it is very tempting to try to apply deep learning techniques that have been remarkably successful in other data-rich settings.

There are multiple flavours to graph learning problems that are largely application-dependent. One dichotomy is between *node-wise* and *graph-wise* problems, where in the former one tries to predict properties of individual nodes in the graph (e.g. identify malicious users in a social network), while in the latter one tries to make a prediction about the entire graph (e.g. predict solubility of a molecule). Furthermore, like in traditional ML problems, we can distinguish between *supervised* and *unsupervised* (or *self-supervised*) settings, as well as *transductive* and *inductive* problems.

Similarly to convolutional neural networks used in image analysis and computer vision, the key to efficient learning on graphs is designing local operations with shared weights that do message passing [5] between every node and its neighbours. A major difference compared to classical deep neural networks dealing with grid-structured data is that on graphs such operations are *permutation-invariant*, i.e. independent of the order of neighbour nodes, as there is usually no canonical way of ordering them.

Despite their promise and a series of success stories of graph representation learning (among which I can selfishly list the [acquisition by Twitter] of the graph-based fake news detection startup Fabula AI I have founded together with my students), we have not witnessed so far anything close to the smashing success convolutional networks have had in computer vision. In the following, I will try to outline my views on the possible reasons and how the field could progress in the next few years.

**Standardised benchmarks **like ImageNet were surely one of the key success factors of deep learning in computer vision, with some [6] even arguing that data was more important than algorithms for the deep learning revolution. We have nothing similar to ImageNet in scale and complexity in the graph learning community yet. The [Open Graph Benchmark] launched in 2019 is perhaps the first attempt toward this goal trying to introduce challenging graph learning tasks on interesting real-world graph-structured datasets. One of the hurdles is that tech companies producing diverse and rich graphs from their users’ activity are reluctant to share these data due to concerns over privacy laws such as GDPR. A notable exception is Twitter that made a dataset of 160 million tweets with corresponding user engagement graphs available to the research community under certain privacy-preserving restrictions as part of the [RecSys Challenge]. I hope that many companies will follow suit in the future.

**Software libraries **available in the public domain played a paramount role in “democratising” deep learning and making it a popular tool. If until recently, graph learning implementations were primarily a collection of poorly written and scarcely tested code, nowadays there are libraries such as [PyTorch Geometric] or [Deep Graph Library (DGL)] that are professionally written and maintained with the help of industry sponsorship. It is not uncommon to see an implementation of a new graph deep learning architecture weeks after it appears on arxiv.

**Scalability** is one of the key factors limiting industrial applications that often need to deal with very large graphs (think of Twitter social network with hundreds of millions of nodes and billions of edges) and low latency constraints. The academic research community has until recently almost ignored this aspect, with many models described in the literature completely inadequate for large-scale settings. Furthermore, graphics hardware (GPU), whose happy marriage with classical deep learning architectures was one of the primary forces driving their mutual success, is not necessarily the best fit for graph-structured data. In the long run, we might need specialised hardware for graphs [7].

**Dynamic graphs **are another aspect that is scarcely addressed in the literature. While graphs are a common way of modelling complex systems, such an abstraction is often too simplistic as real-world systems are dynamic and evolve in time. Sometimes it is the temporal behaviour that provides crucial insights about the system. Despite some recent progress, designing graph neural network models capable of efficiently dealing with continuous-time graphs represented as a stream of node- or edge-wise events is still an open research question.

#deep-learning #representation-learning #network-science #graph-neural-networks #geometric-deep-learning #deep learning

1602261660

In this post, you will get to learn deep learning through a simple explanation (layman terms) and examples.

Deep learning is part or subset of machine learning and not something that is different than machine learning. Many of us, when starting to learn machine learning, try and look for the answers to the question, “What is the difference between machine learning and deep learning?” Well, both machine learning and deep learning are about learning from past experience (data) and make predictions on future data.

Deep learning can be termed as an approach to machine learning where learning from past data happens based on artificial neural networks (a mathematical model mimicking the human brain). Here is the diagram representing the similarity and dissimilarity between machine learning and deep learning at a very high level.

#machine learning #artificial intelligence #deep learning #neural networks #deep neural networks #deep learning basics