# Posts by Category

## Binary Search

Learn about Binary Search which is a simple and very useful algorithm whereby many linear algorithms can be optimized to run in logarithmic time.

## Dynamic Programming

Learn about Dynamic Programming which is a famous and important algorithm for solving problems.

## Sorting

Learn about merge-sort, quick-sort, other sorting algorithms and their running time.

## Codility Lesson14: MinMaxDivision

Sharing an answer code of mine about MinMaxDivision problem of Codility lesson 14.

## Codility Lesson17: NumberSolitaire

Sharing an answer code of mine about NumberSolitaire problem of Codility lesson 17.

## Codility Lesson16: TieRopes

Sharing an answer code of mine about TieRopes problem of Codility lesson 16.

## Codility Lesson15: MinAbsSumOfTwo

Sharing an answer code of mine about MinAbsSumOfTwo problem of Codility lesson 15.

## Codility Lesson9: MaxProfit

Sharing an answer code of mine about MaxProfit problem of Codility lesson 9.

## HackerRank: Is This a Binary Search Tree

Sharing answer codes of mine about HackerRank: Is This a Binary Search Tree.

## Codility Lesson6: MaxProductOfThree

Sharing an answer code of mine about MaxProductOfThree problem of Codility lesson 6.

## Codility Lesson5: PassingCars

Sharing an answer code of mine about PassingCars problem of Codility lesson 5.

## Codility Lesson4: MissingInteger

Sharing an answer code of mine about MissingInteger problem of Codility lesson 4.

## Codility Lesson3: FrogJmp

Sharing an answer code of mine about FrogJmp problem of Codility lesson 3.

## Codility Lesson2: CyclicRotation

Sharing an answer code of mine about CyclicRotation problem of Codility lesson 2.

## Codility Lesson1: Binary Gap

Sharing an answer code of mine about BinaryGap problem of Codility lesson 1.

## Graph

Learn about graph, graph representations, graph traversals and their running time.

## Tree

Learn about tree, tree traversal, binary heap, trie and their running time.

## Stack and Queue

Learn about stack, queue, dequeue, its implementation and running time.

## Hash Table

Learn about hash table, hash function, hash code, its implementation and running time.

## Theano development ends

Theano will not be maintained after the 1.0 release, announced by the MILA group.

## New TensorBoard API is launched that can make you to build your own visualizations

TensorFlow team launched the new customizable TensorBoard API on Sept 11, 2017. As the previous TensorBoard API did not include reusable APIs, it was difficu...

## Mining Objects: Fully Unsupervised Object Discovery and Localization From a Single Image

“Mining Objects: Fully Unsupervised Object Discovery and Localization From a Single Image” focus on performing unsupervised object discovery and localization...

## BING: Binarized Normed Gradients for Objectness Estimation at 300fps

“BING: Binarized Normed Gradients for Objectness Estimation at 300fps” is a an objectness classifier using binarized normed gradient and linear classifier, w...

## U-Net: Convolutional Networks for Biomedical Image Segmentation

“U-Net: Convolutional Networks for Biomedical Image Segmentation” is a famous segmentation model not only for biomedical tasks and also for general segmentat...

## MS-RMAC: Multiscale Regional Maximum Activation of Convolutions for Image Retrieval

“MS-RMAC: Multiscale Regional Maximum Activation of Convolutions for Image Retrieval” improves current Maximum Activation of Convolutions (MAC) feature for i...

## Dual Attention Network for Scene Segmentation

“Dual Attention Network for Scene Segmentation” improves scene segmentation tasks performance by attaching self-attention mechanism. It is in arxiv yet and t...

## Harmonious Attention Network for Person Re-Identification

“Harmonious Attention Network for Person Re-Identification” suggests a joint learning of soft pixel attention and hard regional attention for person re-ident...

## Super-Convergence: very fast training of neural networks using large learning rates

“Super-Convergence: very fast training of neural networks using large learning rates” suggests a different learning rate policy called ‘one cycle policy’ whi...

## DeepLab: Deep Labelling for Semantic Image Segmentation

“DeepLab: Deep Labelling for Semantic Image Segmentation” is a state-of-the-art deep learning model from Google for sementic image segmentation task, where t...

## Gradient Acceleration in Activation Functions

“Gradient Acceleration in Activation Functions” argues that the dropout is not a regularizer but an optimization technique and propose better way to obtain t...

## CBAM: Convolutional Block Attention Module

“CBAM: Convolutional Block Attention Module” proposes a simple and effective attention module for CNN which can be seen as descendant of Sqeeze and Excitatio...

## Re-ID done right

“Re-ID done right: towards good practices for person re-identification” proposes a different approach to use deep network on person re-identification task. I...

## DeepIR

“Deep image retrieval: learning global representations for image search” proposes an approach for instance-level image retrieval. It was presented in the ECC...

## SENet

“Squeeze-and-Excitation Networks” suggests simple and powerful layer block to improve general convolutional neural network. It was presented in the conferenc...

## Regularization and Optimization

This post is a summary and paper skimming on regularization and optimization. So, this post will be keep updating by the time.

## Scale-Invariant Feature Transform (SIFT)

Scale-Invariant Feature Transform (SIFT) is an old algorithm presented in 2004, D.Lowe, University of British Columbia. However, it is one of the most famous...

## Image Retrieval

This post is a summary and paper skimming on image retrieval related research. So, this post will be keep updating by the time.

## Rotation Invariance & Equivariance

This post is a summary and paper skimming on rotation invariance and equivariance related research. So, this post will be keep updating by the time.

## Improved deep metric learning with multi-class N-pair loss objective

“Improved deep metric learning with multi-class N-pair loss objective” proposes a way to handle the slow convergence problem of contrastive loss and triplet ...

## Extreme clicking for efficient object annotation

“Extreme clicking for efficient object annotation” proposes a better way to annotate object bounding boxes with four clicks on the object. It is a further re...

## Detection & Segmentation

This post is a summary and paper skimming on detection and segmentation related research. So, this post will be keep updating by the time.

## Training object class detectors with click supervision

“Training object class detectors with click supervision” proposes efficient way of annotating bounding boxes for object class detectors. It was presented in ...

## Inception-v4 and Inception-ResNet

“Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning” is an advanced version of famous vision model ‘inception’ from Google. It...

## Network In Network

“Network In Network” is one of the most important study related convoutional neural network because of the concept of 1 by 1 convolution and global average p...

## Learning Deep Features for Discriminative Localization

“Learning Deep Features for Discriminative Localization” proposed a method to enable the convolutional neural network to have localization ability despite be...

## Hide-and-Seek

“Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization” proposed a weakly-supervised framework to improve ob...

## Loss Functions

When we train a deep learning model, we need to set a loss function for minimizing the error. The loss function indicates how much each variable contributes ...

## Attention Is All You Need

The paper “Attention is all you need” from google propose a novel neural network architecture based on a self-attention mechanism that believe to be particul...

## Optimization

It is always important what kind of optimization algorithm to use for training a deep learning model. According to the optimization algorithm we use, the mod...

## Vision Technique

Research on several vision techniques such as pixel difference and optical flow.

## Approximate Inference

Approximate inference methods make it possible to learn realistic models from big data by trading off computation time for accuracy, when exact learning and ...

## Autoencoder

Autoencoder is an artificial neural network used for unsupervised learning of efficient codings. The aim of an autoencoder is to learn a representation (enco...

## AI Related Terms

This post will be about artificial intelligence related terms including linear algebra, probability distribution, machine learning and deep learning

Generative Adversarial Networks (GAN) is a framework for estimating generative models via an adversarial process by training two models simultaneously. A gen...

## Regularization

Regularization is important technique for preventing overfitting problem while training a learning model.

## Batch Normalization

‘Batch Normalization’ is an basic idea of a neural network model which was recorded the state-of-the art (4.82% top-5 test error) in the ImageNet competition...

## Probability

Learn about probability which are the basics of artificial intelligence and deep learning.

## Recurrent Neural Network

Learn the basics about Recurrent Neural Network (RNN), its detail and case models of RNN.

## YOLO 9000

‘YOLO9000: Better, Faster, Stronger’ proposed an improved version of YOLO which was presented at IEEE Conference on Computer Vision and Pattern Recognition i...

## Convolutional Neural Network

Learn the basics about Convolutional Neural Network (CNN), its detail and case models of CNN.

## You Only Look Once (YOLO)

‘You Only Look Once: Unified, Real-Time Object Detection’ (YOLO) proposed an object detection model which was presented at IEEE Conference on Computer Vision...

## Faster R-CNN

Faster R-CNN is an object detecting network proposed in 2015, and achieved state-of-the-art accuracy on several object detection competitions.

## Capsule Network

Cpasule Network is a new types of neural network proposed by Geoffrey Hinton and his team and presented in NIPS 2017. As Geoffrey Hinton is Godfathers of Dee...

## TensorFlow

TensorFlow is a machine learning framework that Google created and used to design, build, and train deep learning models. It supports complex and heavy numer...

## Feed-Forward Neural Network (FFNN)

The Feed-Forward Neural Network (FFNN) is the simplest and basic artificial neural network we should know first before talking about other complicated networ...

## Neural machine translation by jointly learning to align and translate

The paper “Neural Machine Translation By Jointly Learning To Align And Translate” introduced in 2015 is one of the most famous deep learning paper related na...

## Activation functions

Let’s talk about activation function in artificial neural network and some questions related of it.

## Multi-Speaker Tacotron in TensorFlow

Today, I am going to introduce interesting project, which is ‘Multi-Speaker Tacotron in TensorFlow’. It is a speech synthesis deep learning model to generate...

## Long-term Recurrent Convolutional Network (LRCN)

There has been a lot of attempt to combine between Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) for image-based sequence recognition...

## Convex optimization problem

When we solve machine learning problem, we have to optimize a certain objective function. One of the case of it is convex optimization problem which is a pro...