Posts by Tag

Adadelta

Optimization

13 minute read

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...

Adagrad

Optimization

13 minute read

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...

Adam

Optimization

13 minute read

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...

BING

CAM

Hide-and-Seek

7 minute read

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

CBAM

CBAM: Convolutional Block Attention Module

4 minute read

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

CEC

Recurrent Neural Network

5 minute read

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

CLR

CNN

Network In Network

4 minute read

“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...

Capsule Network

5 minute read

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...

Codility

DBN

Autoencoder

8 minute read

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

Deep network

Dropout

FFT

GAN

Generative Adversarial Networks (GAN)

4 minute read

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

GAP

GRU

Recurrent Neural Network

5 minute read

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

GoogLeNet

Inception-v4 and Inception-ResNet

1 minute read

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

Information theory

Probability

10 minute read

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

L1 regularization

Regularization

3 minute read

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

L2 regularization

Regularization

3 minute read

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

LSTM

Recurrent Neural Network

5 minute read

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

MAC

MAP

Probability

10 minute read

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

MLE

Probability

10 minute read

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

NAG

Optimization

13 minute read

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...

NIN

Network In Network

4 minute read

“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...

NLP

NMT

Attention Is All You Need

5 minute read

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...

Objectness

PCA

Autoencoder

8 minute read

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

Programmers

R-CNN

Faster R-CNN

3 minute read

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

RBM

Autoencoder

8 minute read

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

RMSprop

Optimization

13 minute read

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...

RNN

Recurrent Neural Network

5 minute read

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

Reference

References about eXplainable AI(XAI)

1 minute read

The eXplainable Artificial Intelligence (XAI) is an artificial intelligence model that is able to explain its decisions and actions to human users.

ResNet

Inception-v4 and Inception-ResNet

1 minute read

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

SENet

Re-ID done right

5 minute read

“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

5 minute read

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

SENet

4 minute read

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

SGD

Optimization

13 minute read

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...

TensorBoard

TensorFlow

Theano

Theano development ends

less than 1 minute read

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

U-Net

XAI

References about eXplainable AI(XAI)

1 minute read

The eXplainable Artificial Intelligence (XAI) is an artificial intelligence model that is able to explain its decisions and actions to human users.

YOLO

YOLO 9000

less than 1 minute read

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

You Only Look Once (YOLO)

4 minute read

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

activation function

Activation functions

7 minute read

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

algorithm

Binary Search

3 minute read

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

3 minute read

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

Sorting

4 minute read

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

approximate inference

Approximate Inference

3 minute read

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

array

attention

Attention Is All You Need

5 minute read

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...

attention network

autoencoder

Autoencoder

8 minute read

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

11 minute read

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

batch normalization

Batch Normalization

5 minute read

‘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...

binary heap

Tree

4 minute read

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

Binary Search

3 minute read

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

binary search tree

binary tree

bit manipulation

bounding box

capsule network

Capsule Network

5 minute read

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...

class activation map

click supervision

cnn

contrastive loss

convex optimization problem

Convex optimization problem

2 minute read

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...

convolution

cross entropy

Loss Functions

3 minute read

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 ...

data structure

Graph

5 minute read

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

Tree

4 minute read

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

Stack and Queue

3 minute read

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

Hash Table

3 minute read

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

deep learning

TensorFlow

8 minute read

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...

Keras

less than 1 minute read

Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano. This article is about summary and ...

deeplab

dequeue

Stack and Queue

3 minute read

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

dropout

Regularization

3 minute read

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

dynamic programming

Dynamic Programming

3 minute read

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

entropy

Probability

10 minute read

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

exploding gradient

Recurrent Neural Network

5 minute read

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

fast R-CNN

Faster R-CNN

3 minute read

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

faster R-CNN

Faster R-CNN

3 minute read

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

ffnn

Feed-Forward Neural Network (FFNN)

1 minute read

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

gap

Network In Network

4 minute read

“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...

generalization

Regularization

3 minute read

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

global average pooling

gradient descent

Optimization

13 minute read

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...

graph

Graph

5 minute read

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

hackerrank

hash table

Hash Table

3 minute read

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

heap

hide-and-seek

Hide-and-Seek

7 minute read

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

image retrieval

Regularization and Optimization

1 minute read

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

Image Retrieval

4 minute read

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

inception

Inception-v4 and Inception-ResNet

1 minute read

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

keras

Keras

less than 1 minute read

Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano. This article is about summary and ...

learning rate

linked_list

loss function

Loss Functions

3 minute read

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 ...

lrcn

math

metric learning

n-pair loss

object annotation

object detection

Hide-and-Seek

7 minute read

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

YOLO 9000

less than 1 minute read

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

You Only Look Once (YOLO)

4 minute read

‘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

3 minute read

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

objectness

optical flow

Vision Technique

2 minute read

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

optimization

Optimization

13 minute read

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...

paper

paper skimming

Regularization and Optimization

1 minute read

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

Image Retrieval

4 minute read

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

13 minute read

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.

Detection & Segmentation

3 minute read

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

pixel difference

Vision Technique

2 minute read

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

probability

Probability

10 minute read

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

queue

Stack and Queue

3 minute read

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

re-identification

recursion

regularization

Regularization

3 minute read

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

Batch Normalization

5 minute read

‘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...

residual

Inception-v4 and Inception-ResNet

1 minute read

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

rnn

rotation equivariance

Rotation Invariance & Equivariance

13 minute read

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.

rotation invariance

Rotation Invariance & Equivariance

13 minute read

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.

scene segmentation

segmentation

sift

Scale-Invariant Feature Transform (SIFT)

4 minute read

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...

sorting

Sorting

4 minute read

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

speech synthesis

Multi-Speaker Tacotron in TensorFlow

3 minute read

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...

stack

Stack and Queue

3 minute read

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

string

super convergence

tensorflow

TensorFlow

8 minute read

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...

tools

TensorFlow

8 minute read

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...

Keras

less than 1 minute read

Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano. This article is about summary and ...

traversal

Tree

4 minute read

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

tree

Tree

4 minute read

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

trie

Tree

4 minute read

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

triplet loss

unsupervised

vanishing gradient

Recurrent Neural Network

5 minute read

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

variational inference

Approximate Inference

3 minute read

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

vision

Vision Technique

2 minute read

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

weakly-supervised object

Hide-and-Seek

7 minute read

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