Deep Learning

Types of Gradient Optimizers in Deep Learning

In this article, we will explore the concept of Gradient optimization and the different types of Gradient Optimizers present in Deep Learning such as Mini-batch Gradient Descent Optimizer.

Deep Learning

109 Deep Learning projects [with source code]

In this article, we have listed 109 Deep Learning projects that will help you boost your Portfolio. We have provided resources to explore the project ideas further along with source code. You can do this as a part of your College Project (B.Sc, M.Sc and even PhD) or take it up for your portfolio.

Deep Learning

The Vision Transformer

In 2020, Alexey Dosovitskiy et al used the transformer model to build a new network for image recognition called the vision transformer, that we will try to explain and to implement in this article.

Deep Learning

VGG54 and VGG22

VGG54 and VGG22 are loss metrics to compare high and low resolution images by considering the feature maps generated by VGG19 neural network model.

Deep Learning

Gradient Accumulation [+ code in PyTorch]

Gradient Accumulation is an optimization technique that is used for training large Neural Networks on GPU and help reduce memory requirements and resolve Out-of-Memory OOM errors while training. We have explained the concept along with Pytorch code.

Deep Learning

Calculate mean and std of Image Dataset

In this article, we have explained how to calculate the mean and standard deviation (std) of an image dataset which can be used to normalize images in the dataset for effective training of Neural Networks.

Machine Learning (ML)

Backpropagation vs Gradient Descent

Hello everybody, I'll illustrate in this article two important concepts in our journey of neural networks and deep learning. Welcome to Backpropagation and Gradient Descent tutorial and the differences between the two.

Machine Learning (ML)

EfficientNet [model architecture]

Convnet have hit the memory limit it is time to look for more efficient ways to improve the accuracy. For that, we introduce in this article the EfficientNet model that suggests an efficient way for improving the performance of Convnets.

Machine Learning (ML)

GELU vs ReLU

In this article, we have explored the differences between GELU (Gaussian Error Linear Unit) and ReLU (Rectified Linear Unit) activation functions in depth.

Machine Learning (ML)

Activation function GELU in BERT

In BERT, GELU is used as the activation function instead of ReLU and ELU. In this article, we have explained (both based on experiments and theoretically) why GELU is used in BERT model.

Machine Learning (ML)

YOLO v5 model architecture [Explained]

Since 2015 the Ultralytics team has been working on improving this model and many versions since then have been released. In this article we will take a look at the fifth version of this algorithm YOLOv5.

Machine Learning (ML)

Radial Basis Function Neural Network

Radial Basis Function Neural Network (RBFNN) is one of the shallow yet very effective neural networks. It is widely used in Power Restoration Systems.

Machine Learning (ML)

Delta Rule in Neural Network

We shall be discussing Delta rule in neural networks that is used to updated weights during training a Neural Network.

Machine Learning (ML)

Kohonen Neural Network

The Kohonen Neural Network (KNN) also known as self organizing maps is a type of unsupervised artificial neural network. This network can be used for clustering analysis and visualization of high-dimension data.

List of Interview Questions

BERT Interview Questions (NLP)

In this article, we will go over various questions that cover the fundamentals and inner workings of the BERT model.

Machine Learning (ML)

XNet architecture: X-Ray image segmentation

Medical image processing is an important application in Computer Vision,requires segmentation of images into body parts. Joseph Bullock and his partners in Durham University proposed a neuron network called XNet which is suitable for this task.

Machine Learning (ML)

Seq2seq: Encoder-Decoder Sequence to Sequence Model Explanation

In Deep learning, we all know that Recurrent Neuron Network solves time series data. Sequence to Sequence (or Seq2Seq for short) is a kind of model that was born to solve "Many to many" problem.

Machine Learning (ML)

Super Resolution GAN: SRGAN

Super Resolution GAN (SRGAN) is generative adversarial network that can generate high resolution images from low resolution images using perceptual loss function that is made of the adversarial loss as well as the content loss.

Deep Learning

Interview Questions on Transformers

The Transformers architecture introduced in the paper “Attention Is All You Need”, has changed the scenario of creating more complex and advanced NLP models. Following are the important questions for an interview on Transformers.

data science

How is Deep Learning used for Data Science tasks?

In this article, we will see how deep learning is used in Data Science.

List of Interview Questions

Interview questions on GAN

In this article, we have presented several Interview questions on Generative Adversarial Network (GAN) along with detailed answers.

Machine Learning (ML)

Drone simulation with object detection

Drones are Unmanned Aerial Vehicles (UAV) that are remotely controlled either by humans or by computer programs. They range in size from under one pound to several hundred pounds.

Machine Learning (ML)

Panoptic Segmentation

Panoptic Segmentation is an improved human-like image processing approach that combines the goals of both Instance and Semantic Segmentation. It was first proposed in a 2018 paper by Alexander Kirillov.

Deep Learning

Deep Learning Practice Questions

In this article, we will be going over 50 practice questions related to deep learning.

Machine Learning (ML)

Confusion matrix and how accuracy is not the key always

Confusion matrix is a term in the field of machine learning which is generally associated with a lot of confusion on what it means, which is exactly what will be removed in this article as we understand confusion matrix.