Code360 powered by Coding Ninjas X Naukri.com. Code360 powered by Coding Ninjas X Naukri.com

Last updated: Feb 7, 2022

Deep Learning

Deep learning is a more advanced methodology than Machine Learning, which encompasses supervised, unsupervised, and recommendation systems. It is made up of various algorithms and neural networks, such as Convolution Neural Network (CNN) and Recurrent Neural Network (RNN), which have a wide range of real-world applications.

Deep Learning vs Neural Networks MEDIUM

This article will discuss the differences between Deep learning and Neural networks.

Author yuvatimankar

1 upvote

Artificial Intelligence in Education EASY

In this blog, we will see the different ways in which AI is transforming education. We will explore its benefits and challenges.

0 upvotes

Features of Artificial Intelligence EASY

In this blog, we will learn about Features of Artificial Intelligence. Get ready to understand how AI is shaping our world & what makes it so powerful. .

Author Pallavi singh

0 upvotes

Deep Learning vs NLP MEDIUM

In this article, we will discuss what deep learning and Natural Language Processing (NLP) are, along with various differences between them.

Author Abhiyodaya Pandey

1 upvote

Data Analytics MEDIUM

In this blog, we will learn about Data Analytics. We will understand its core concepts, its usage, and much more for better understanding.

Author Gunjan Batra

0 upvotes

Artificial Intelligence Books EASY

In this blog, we will explore about Artificial Intelligence Books.

Author Gaurav Gandhi

0 upvotes

Decision Tree Induction in Data Mining MEDIUM

In this blog, we will learn about Decision Tree Induction in Data Mining along with it working, advantages and disadvantages.

Author Riya Singh

0 upvotes

Deep Learning vs Reinforcement Learning MEDIUM

This article covers the concept of deep learning and reinforcement learning and their differences.

Author 3053_Jatin

1 upvote

Deep Learning vs Data Science

In this blog, we will discuss Deep Learning vs Data Science and explore various use cases of Deep Learning and Data Science.

Author Aditya_2bc4

0 upvotes

Deep Learning vs CNN EASY

This blog will discuss the topic of Deep Learning vs CNN, including the definition, features, pros and cons.

Author Sagar Mishra

0 upvotes

Image Captioning MEDIUM

In this article, we will understand Image captioning. We will see its working, types of architectures, phases, and applications.

1 upvote

Image Caption Generator MEDIUM

This article will teach you how to build an image caption generator.

Author Abhinav Anand

0 upvotes

Fuzzy Logic: Definition, Examples, and History MEDIUM

Fuzzy logic processes variables with multiple truth values, accommodating imprecise data for more accurate conclusions in various applications like AI and control systems.

Author simransri

0 upvotes

Introduction

Deep Learning entails creating models and algorithms, as well as allowing the computer to learn and implement on its own. Understand the fundamentals and applications of deep learning.

Introduction to Deep Learning

This blog is an overview of deep learning and its real-world applications.

Author Arun Nawani

4 upvotes

Introduction To Geometric Deep Learning

This article will see an overview and introduction to Geometric Deep Learning application of geometric deep learning.

0 upvotes

McCulloch Pitt's Model of Neuron EASY

In this blog, we’ll discuss the first ANN ever developed, The McCulloch Pitt's Model of Neuron.

Author Arun Nawani

0 upvotes

Concepts and Tools

Learn about important deep learning concepts that will help you throughout the learning process, as well as tools that will help you build models and improve algorithms, such as Tensorflow, KERAS, and PyTorch.

Binary Classification

In this blog we have discussed Binary Classification, followed by developing, visualizing the Model.

Author Mandla Dharani

1 upvote

This blog will study vectorization and use it in Machine Learning to write cleaner and optimized code.

Author Chaturvedi

4 upvotes

Residual Analysis MEDIUM

In this blog, we will learn about Residual Analysis. We will further in the blog, learn about residual analysis in Python.

Author Gunjan Batra

1 upvote

Vectorizing Logistic Regression

In this article, we will discuss the vectorized form of logistic regression. Furthermore, we will implement code for the vectorized form of logistic regression.

Author soham Medewar

4 upvotes

Understanding Forward Propagation

This blog thoroughly discusses Forward propagation in ANNs and how it differs from Backpropagation.

Author Arun Nawani

1 upvote

TensorFlow vs. PyTorch vs. Keras

In this blog, we will see three deep learning frameworks: Keras, TensorFlow, and PyTorch and their use cases. Let's begin.

Author Rajkeshav

0 upvotes

Perceptron One of the fundamental algorithms for working on classification in neural networks. Learn about its implementation, significance, and visualisations.

Tensorflow Tensorflow should not be overlooked when learning and implementing deep learning models. One of the most important tools, with numerous built-in libraries and packages, that allows you to build models more quickly and efficiently.

KERAS KERAS is a popular library for working with neural networks and is an exclusive interface for working with Tensorflow. Reliable tool for managing the backend operations of deep learning models.

PyTorch This is a well-known library for machine learning and deep learning applications. Its packages and methods can also be applied to NLP and computer vision models. Supported by Facebook's research lab.

Theano Discover an important and fascinating Python library for mathematical expressions. Widely used for array operations with improved efficiency and optimization, it also includes integrated support from the GPU and NumPy library.

Caffe2 Caffe2 is a C++-based library that also supports Python and MATLAB. It is widely used for Deep Learning operations, with a wide range of architectures and maps ranging from neural networks to encoders. Caffe2 is now part of PyTorch, but it is still useful.

SparkML SparkML is an abbreviation for Apache Spark's Machine Learning library. It is quicker and includes API for pipelining. In this category, you can learn about its features, pipelining methods in SparkML, and much more.

Miscellaneous Learn about other Deep Learning and Machine Learning-based libraries and packages, as well as their applications and implementations for creating and solving interesting deep learning models and algorithms.

Neural Networks

Neural networks are the foundation of deep learning. A network for prediction and accuracy is built by combining various nodes that are arranged in a meaningful structure. Artificial Neural Networks are another name for them. Learn about its different types, applications, and hands-on experience.

Artificial Neural Networks

This blog provides a high-level view of ANNs, particularly their architecture and their uses in the real world.

Author Arun Nawani

0 upvotes

Graph Neural Networks MEDIUM

In this article on Graph Neural Networks (GNN), we will understand GNN's fundamentals, syntax, practical examples with code and output, etc.

Author Kanak Rana

0 upvotes

Multilayer Perceptron

The objective of this blog is to understand what multilayer perceptrons are.

0 upvotes

Loss Functions in Neural Networks

In this article, we will learn about the loss function in neural networks. We’ll see some importance and types of loss functions.

Author Kanak Rana

0 upvotes

What is Neural Network EASY

In this article, we will explore what is Neural Network, how they work, and the different types of neural networks. We will also see a simple implementation of a neural network using Python.

Author Riya Singh

0 upvotes

Quantization and Pruning

This blog post will explore two crucial techniques. - Quantization and Pruning. - that enables the development of efficient deep neural networks while maintaining accuracy.

0 upvotes

Introduction to Hopfield Neural Network

This blog discussed an introduction to Hopfield neural network. We will also discuss its architecture, energy function, and training model.

Author Ayushi Goyal

0 upvotes

Feedforward Neural Networks A feedforward neural network is one that does not have a cycle. Learn about its concept, implementation, and backpropagation.

Optimization of Neural Network Learn about different algorithms, architectures, and techniques for optimising neural networks for better prediction and analysis, as well as improving the accuracy of any model.

Eigenvalues and Eigenvector Linear algebra is used in machine learning and deep learning. Learn about Eigenvalues and Eigenvectors, which can aid in the reduction of equations and matrices when working on models.

Convolution Neural Network

Convolution Neural Network (CNN) is a sophisticated deep learning algorithm that works best with images. It classifies images based on their various features. Because it is a deep learning algorithm, it can learn and implement at various stages of training.

Understanding of Convolutional Neural Network

The objective of this blog is to understand the Convolution Neural Network.

0 upvotes

Padding in Convolutional Neural Network MEDIUM

This article discusses the padding in convolutional neural network in detail. It also discusses the need for padding and its use cases.

0 upvotes

Convolution Layer

In this blog, we’ll see what convolution is and how to build a simple convolutional neural network to classify MNIST Digits.

Author Chaturvedi

1 upvote

Stride in Convolutional Neural Network (CNN) MEDIUM

Discover how stride impacts convolutional neural networks (CNNs). This article will cover topics like Stride in convolutional neural network, differences between stride and padding, and the effects of stride.

Author yesdhruv

0 upvotes

Pooling Layer in Convolutional Neural Network MEDIUM

This article discusses the Pooling Layer in Convolutional Neural Networks.

Author Abhinav Anand

1 upvote

Convolution layer, Padding, Stride, and Pooling in CNN

The objective of this blog is to understand various layers of Convolution Neural Networks.

1 upvote

Data Augmentation

In this blog, we discussed data augmentation, sample model, horizontal and vertical augmentation followed by brightness augmentation.

Author Mandla Dharani

0 upvotes

Softmax and Cross-Entropy EASY

This article will study softmax function and cross-entropy with their implementation. Further, we will see why cross-entropy is used with the softmax function.

Author Mayank Goyal

0 upvotes

VGG-16 - CNN Model EASY

This blog will provide you with an overview of the VGG-16 and illustrate it using an object detection use case. Explore vgg16 architecture with its implementations.

Author Md Yawar

0 upvotes

In this article, we will learn about the architecture of the AlexNet with implementation. Important terminologies that are needed to build the AlexNet architecture.

Author soham Medewar

0 upvotes

Classic ConvNet Architectures HARD

This article discusses the different Classic ConvNet architectures with detailed explanations.

2 upvotes

This blog focuses on the approach and architecture of ZFNet

Author Mohammad Yawar

0 upvotes

VGG Network EASY

VGG, a classic convolutional neural network (CNN) architecture discussed in this blog.

Author Priyanshu Sharma

0 upvotes

This blog aims to explain what inceptionNet is and elucidate the evolution of its versions.

Author Md Yawar

0 upvotes

ResNet Architecture EASY

This article focuses on the concept, need, architecture, and implementation of ResNet.

Author Md Yawar

0 upvotes

GoogLeNet Model EASY

This article discusses googlenet architecture, features of google net architecture, and advantages of google net with faqs.

Author Chaturvedi

0 upvotes

Visualizing Convolutional Neural Networks with Filters

This blog explains the convolutional neural network. In detail, we will discuss how to enter visualizations in CNN, visualize convolutional layers, pre-fit the VGG model, how to visualize filters, and many more.

0 upvotes

Guided Backpropagation

In this article, we will discuss guided backpropagation, use of guided backpropagation along with an example and a code implementation of it.

Author soham Medewar

1 upvote

Fooling Convolutional Neural Network

This blog will focus on the basics behind the fooling of Convolution neural networks. Let's begin.

Author Rajkeshav

0 upvotes

Dense In Deep Learning EASY

This article will focus on the denser layer in neural networks, different hyperparameters of Keras dense layer, and finally, a basic implementation.

Author Mayank Goyal

0 upvotes

Hands-on CNN The theory and implementation of various Convolution Neural Network techniques have been discussed. Learn about the various applications of CNNs, as well as their implementation and operation. Create intriguing models that can be used to solve real-world problems.

Regularization

Regularization is a Deep Learning method for reducing noise and complexity in any model in order to avoid further complications such as overfitting. It is an important technique that can be used to significantly improve the model's overall performance.

Bias variance tradeoff EASY

The blog discusses the bias-variance tradeoff in detail and how it can be dealt with.

Author aniket verma

0 upvotes

Early Stopping In Deep Learning

This article is about early stopping in deep learning and how it can solve the problem of overfitting

Author Mohammad Yawar

1 upvote

Parameter Sharing and Tying

In this article, we will learn about parameter sharing and tying and there use. Further, we will see the issues faced by l1 and how GROWL overcomes those issues.

Author Mayank Goyal

2 upvotes

Noise Injection in Neural Networks EASY

In this article, we try to discuss the concept of noise injection in neural networks and how it will work in neural networks by adding noise to the network to reduce overfitting.

Author Vamsi Viswanadham

0 upvotes

Ensemble Method

This blog will look up Ensemble learning technique and implementation from scratch.

Author Rajkeshav

0 upvotes

Dropout - Regularization Method

In this article, we will learn a powerful regularization technique i.e., dropout. Also will discuss, its uses.

Author soham Medewar

0 upvotes

Greedy Layer-wise Pre-Training HARD

In this article, we will learn greedy layer-wise pre-training in deep learning neural networks. Also, we will implement code for it.

Author soham Medewar

3 upvotes

Activation Functions - Introduction

Activation functions are the most essential aspect of any neural network as they are functions that help train neural networks in accordance with the data given.

Author Tushar Tangri

0 upvotes

Neural Network Activation Functions EASY

This article aims to understand various activation functions.

0 upvotes

Batch Normalization - Introduction

In this blog, you will learn about the batch normalization method used to accelerate the training of deep learning neural networks.

Author Priyanshu Sharma

0 upvotes

Batch Normalization - Implementation

This blog focuses on Batch normalization and its implementation.

Author Mohammad Yawar

0 upvotes

Recurrent Neural Networks

Recurrent Neural Networks are another type of Deep Learning Neural Network (RNN). It has memory, which is a key feature of RNN. Discover its architecture, implementation, and applications.

Recurrent Neural Network - Intro

In this blog, we discussed working, advantages, disadvantages, applications of the recurrent neural network(RNN)

Author Mandla Dharani

0 upvotes

Understanding an RNN cell

The objective of this blog is to understand RNN cells.

0 upvotes

Understanding Bidirectional RNN MEDIUM

This blog will discuss Bidirectional RNN with suitable code examples, some advantages and disadvantages along with some frequently asked questions.

Author Aayush Sharma

0 upvotes

Sequence Models

In this article, we are going to discuss sequence models. Also, we will discuss in detail Recurrent Neural Network(RNN) and Long Short-Term Memory(LSTM).

Author soham Medewar

0 upvotes

Unrolling Recurrent Neural Network

This blog will focus on the requirements of Recurrent Neural Networks over Artificial Neural Networks.

Author Rajkeshav

0 upvotes

Backpropagation Through Time-RNN

This article will look into BPTT, its algorithm, limitations, and advantages over normal Backpropagation.

Author Mayank Goyal

1 upvote

In this article, we will discuss truncated backpropagation through time (BPTT). Also will learn different techniques that will help in learning Truncated BPTT.

Author soham Medewar

0 upvotes

Gated Recurrent Units (GRUs) EASY

This article talks about the architecture and working of GRUs.

Author Mohammad Yawar

0 upvotes

Time Series Prediction with GRU

In this article, we will read about Time-series Prediction with GRU. We will compare it with LSTM and see an example.

Author Sayed Fahim Ali Dawdye

0 upvotes

Long Short Term Memory(LSTM) Cells

This article will study LSTM cells, their working, architecture, and some of their applications.

Author Mayank Goyal

0 upvotes

Solving the Vanishing Gradient Problem with LSTM

In this article, we will discuss how the vanishing gradient problem is solved using LSTM (long short-term memory). Also, will see why simple RNN’s face this problem.

Author soham Medewar

0 upvotes

Bidirectional LSTM

In this article, we will learn the functioning of bi-directional long short-term memory(LSTM). Also will understand how to use Bi-LSTM in keras.

Author soham Medewar

1 upvote

Stock Price Prediction Using LSTM

This article will study stock price prediction using the LSTM model and implement the same.

Author Mayank Goyal

0 upvotes

Encoder-Decoder Models

This article study about the encoder-decoder model, its architecture, it's working, and some of the applications.

Author Mayank Goyal

0 upvotes

Hands-on Recurrent neural networks are among the most interesting and straightforward neural networks. Learn more about their applications, use cases, and hands-on projects that can be used in real-world data analysis and prediction.

Unsupervised Deep Learning

Unsupervised learning is similar to Machine Learning in that it does not use trained data but has a long list of real-world applications and is widely used by many tech companies. Discover more about autoencoders and the Boltzmann machine.

Self Organizing Maps

This article will study self-organizing maps, their working, and architecture. Lastly, we will see a basic implementation of it.

Author Mayank Goyal

0 upvotes

Autoencoders An unsupervised learning neural network with encoder and decoder that can reduce noise. Discover its various types and code implementation.

Boltzmann Machine Another unsupervised deep learning system with interconnected nodes, including visible and hidden nodes, is the Boltzmann Machine. The algorithm is the algorithm of choice for detecting model irregularities or inconsistencies.

Generative Adversarial Networks (GANs)

GANs, or Generative Adversarial Networks, are a popular unsupervised learning algorithm that learns on its own from given data and predicts for new data. One of the most intriguing Deep Learning approaches. StyleGAN and CycleGAN are two examples of applications.

Generative Adversarial Network

This blog will focus on an exciting AI tool used in machine learning called the Generative Adversarial Network and its applications. Let's begin.

Author Rajkeshav

0 upvotes

Building GAN - Implementation

In this article, we will see a brief introduction to GAN(Generative Adversarial Network). Also will implement a GAN model to support the theory.

Author soham Medewar

0 upvotes

Model Collapse in GANs

This blog will focus on the model collapse in Generative adversarial network and the ways to tackle it.

Author Rajkeshav

0 upvotes

Human Face Generation using GAN

This blog explains the details of Human Face Generation using GAN along with its working, details of generator and discriminator, and Training the GAN Model.

Author kittusinghkumar

0 upvotes

Deep Convolutional Generative Adversarial Networks

This blog will focus on The Deep Convolutional Generative Adversarial network and the detailed implementation.

Author Rajkeshav

0 upvotes

Style based GAN

This blog talks about style based GAN or styleGAN

Author Md Yawar

0 upvotes

Introduction to CycleGAN EASY

In this article, we are going to learn the basics of CycleGANs, its architecture, why we are going to use it, what its advantages are, and also go through its uses.

Author Vamsi Viswanadham

0 upvotes

Introduction to Conditional GANs

In this blog, we will discuss various types of GANs in deep learning, Conditional GANs, flexibility, and Application of Conditional GANs.

Author Aditya_2bc4

0 upvotes

Super Resolution GAN EASY

This article will showcase the concept of Super-Resolution GAN, how it works to increase the resolution of an image, what its architecture is, its usage, etc.

Author Vamsi Viswanadham

0 upvotes

Auxiliary Classifier GAN EASY

In this article, we will learn about the concept of Auxiliary classifier Gan how it works and its code implementation.

Author Adya_Tiwari

2 upvotes

Recommendation Engine

One of the main applications of a recommendation engine is learning from what customers usually visit, purchase, choose, or use and recommending preferences based on that. These are designed to make recommendations based on previous inputs. This model is used by companies such as Netflix, Spotify, and Amazon to provide preferences to their customers.

Recommendation Engine - Introduction

This article will focus on the recommendation system theory, uses types and steps to create one.

Author Mayank Goyal

0 upvotes

Recommendation Engine

In this blog post, we'll learn to implement a recommendation engine using various Python libraries.

Author Shabeg Singh Gill

0 upvotes

Attention Mechanism

Attention Mechanism is a very intelligent algorithm that remembers and provides special features based on the input data. It is widely used in Natural Language Processing and is regarded as one of the most significant breakthrough algorithms for NLP applications.

Attention Mechanism for Image Processing

In this article, we will understand the concept of the attention mechanism and will learn how to use the attention mechanism in image processing by implementing a small model.

Author soham Medewar

0 upvotes

Hierarchical Attention Network

This blog will teach the concept behind Hierarchical Attention Network its use cases, and implementation.

Author Rajkeshav

0 upvotes

Transfer Learning

Transfer Learning is the most advanced Deep Learning technique. It learns from one problem using inputs, outputs, data, and processes, and then uses that data to solve other problems with the same background. This can be extremely useful in solving similar types of problems where the user is not required to enter data every time.

Transfer Learning-Introduction

The objective of this blog is to give an overview of Transfer Learning.

Author aniket verma

0 upvotes

Transfer Learning - Implementation EASY

This blog covers transfer learning with an emphasis on its practical implementation in python.

Author Arun Nawani

0 upvotes

Applications of Deep Learning

Without applications and real-world implementation, any domain is incomplete. Deep Learning is widely used in a variety of fields such as information technology, healthcare, sports, e-commerce, and business analytics. Deep learning can handle everything from Amazon's recommendation system to precision medicine.