SlideShare a Scribd company logo
1 of 24
Download to read offline
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Issues
Summary
Deep Learning
A brief explanation
Keunwoo.Choi
@qmul.ac.uk
Centre for Digital Music, Queen Mary University of London, UK
1/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Issues
Summary
1 Introduction
2 Machine-Learning
3 Deep learning
Overview
Nonlinearity
Weights
SGD
Training
4 Issues
Overfitting
Batch processing
Back-propagation
Other architectures
ImageNet
5 Summary
2/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Issues
Summary
Keunwoo Choi
PhD, QMUL, EECS, c4dm, 2014-present
Supervised by Mark Sandler and George Fazekas
Music Recommendation, (Deep) Machine Learning
Internship, Naver Labs, July-Oct 2015
Visiting PhD, New York University, July-Dec 2016
ETRI, 2011-2014
3D Audio (WFS)
Master’s, SNU EECS, 2009-2011
Applied Acoustics Laboratory, 3D Audio,
Music Signal Processing
Bachelor. SNU EECS, 2005-2009
3/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Issues
Summary
Research Topics
Music Feature Extractions
Analysis of deep CNNs (ISMIR LDB 2015, MLSP 2016)
Auto-Tagging using deep CNN (ISMIR 2016)
Playlist Generation
RNN-based playlist generation (ICML workshop 2016)
Music Captioning
Automatic Composition
Text-based chords and drums (CSMC 2016)
4/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Issues
Summary
Machine Learning
More correctly, supervised learning
Given a goal
Given data x, y
Train an algorithm that best matches x ! y
and validated using unseen x (good generalisation)
”Do not memorise the examples!”
Conventional approaches:
Feature extraction + Classifier
Researchers and experts hand-craft the features
Classifier (e.g. SVM) is trained to achieve the goal
5/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Issues
Summary
Machine Learning
Problems of the conventional approaches
Hand-crafting takes resources
E.g. MFCCs (speech recognition), Histogram of Gradient,
SIFT (computer vision)
Hand-crafting is not automatically optimisable
but a Jang-in-jeong-sin thingy.
Is a Jang-in better than machines?
6/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Overview
Nonlinearity
Weights
SGD
Training
Issues
Summary
NN vs. DNN
1
Logistic regression: No hidden layer
Neural Networks: 1 hidden layer
Deep NN: N hidden layers (N>1)
1
extremetech.com
7/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Overview
Nonlinearity
Weights
SGD
Training
Issues
Summary
DEMO
TensorFlow Playground
Logistic regression: No hidden layer
Neural Networks: 1 hidden layer
Deep NN: N hidden layers (N>1)
Logistic regression Logistic regression fails
NN works well! NN fails
Shallow NN is okay The bigger, the better
8/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Overview
Nonlinearity
Weights
SGD
Training
Issues
Summary
DL Overview
A motivation to deep leanring
Brain and human sensory system
Neurons are identical
Many (100B) identical neurons with suitable structures
Human learns by examples
Human sensory systems are deep
Parallel and serial neuron structure
9/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Overview
Nonlinearity
Weights
SGD
Training
Issues
Summary
DL Overview
A motivation to deep leanring
Do not need to hand-craft features
Black box includes [feature extraction ! classifier]
The whole procedure is computationally optimised to
achieve the goal
by iterative, heavy-computational methods
have outperformed many Jang-in’s
10/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Overview
Nonlinearity
Weights
SGD
Training
Issues
Summary
Comparison
Example task: Speech recognition
Method Conventional ML Deep Learning
Feature
MFCCs
(FFT ! mel-scale
aggregation!
DCT!time-
derivative!ignore first
coe↵!..)
FFT!NN
Classifier SVM, GMM NN
Every computation, parameters, weights is automatically
decided by during training
11/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Overview
Nonlinearity
Weights
SGD
Training
Issues
Summary
DL
Nonlinearity
Single layer performs a nonlinear mapping using
Let x=input vector, y=output vector,
NN: y = 2(W2 1(W1x))
DNN: Stacked (=deep) layers perform a more nonlinear
and complex mapping
y = 6(W6 5(W5 4(W4 3(W3 2(W2 1(W1x))))))
Stacked layers = stacked Nonlinearity! 2
Multiple linear layers, otherwise, can be compressed into
one layer
2
best explained in Colah’s blog
12/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Overview
Nonlinearity
Weights
SGD
Training
Issues
Summary
DL
Weights (= parameters)
NN = nonlinear () and weights W
For (), we use ReLU and its variants
DNN = Combination of ReLU and many Wi ’s
We want...
the network to be trained to do the all dirty works -
feature extraction and classification
(=Wi ’s that do what we order to do)
the network to learn by examples
(=find the optimal W using training data)
How do we train? ! SGD
13/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Overview
Nonlinearity
Weights
SGD
Training
Issues
Summary
Deep Learning
How it learns - by SGD!
SGD: Stochastic Gradient Descent
SGD computationally finds w so that J(w) is minimised
SGD iteratively finds w so that J(w) is minimised
SGD gradually finds w so that J(w) is minimised
w is updated to minimise J(w)
(J(w) J(w) @J(w)
@w )
...if J(w) is di↵erentiable
14/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Overview
Nonlinearity
Weights
SGD
Training
Issues
Summary
Deep Learning
How it learns - by SGD!
Loss function J(w)
A function that we want to minimise to achieve the goal
yestimation = 4(W4 3(W3 2(W2 1(W1x))))
ytrue is given in the dataset
E.g. l2: J(w) = (yestimation ytrue)2
Loss function measures how well the current algorithm is
performing
15/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Overview
Nonlinearity
Weights
SGD
Training
Issues
Summary
Deep Learning
How it learns
We have (a set of) x and ytrue (aka dataset)
We decide a loss function
yestimation = 4(W4 3(W3 2(W2 1(W1x))))
J(w) = a function of (yestimation, ytrue)
w is updated and becomes better weights
= training is performed by SGD
= the DNN is optimised
16/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Overview
Nonlinearity
Weights
SGD
Training
Issues
Summary
Deep Learning
The whole learning procedure
Prepare a training dataset (x, y)
Get a DNN configured (number of layers, nodes, loss
function)
for many times:
for every x, y: (do SGD)
compute yestimation = f (x, w) (go through DNN)
update W according to the current loss,
loss(ytrue , yestimation)
Done!
17/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Overview
Nonlinearity
Weights
SGD
Training
Issues
Summary
Break!
Q&A
playground.tensorflow.org
18/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Issues
Overfitting
Batch processing
Back-
propagation
Other
architectures
ImageNet
Summary
Overfitting
Overfitting
When the network memorises the training data and fails to
generalise
3
A general problem in ML
Example: ,
3
hrefhttp://cs231n.github.io/neural-networks-3/cs231n
19/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Issues
Overfitting
Batch processing
Back-
propagation
Other
architectures
ImageNet
Summary
Batch Gradient Descent
Batch Gradient Descent
Compute GD with seeing more than 1 examples simultaneously
Every computation of
yestimation = 4(W4 3(W3 2(W2 1(W1x))))
is done by matrix computations
Quicker in GPU (because GPU is specialised at computing
large matrix computations)
Less zig-zag
4
4
www.holehouse.org
20/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Issues
Overfitting
Batch processing
Back-
propagation
Other
architectures
ImageNet
Summary
Back-propatagion
aka backprop
5
The essence inside Gradient Descent of NN
The way to compute the derivatives of all weights, @J(w)
@w
so that J(w) can be updated as J(w) @J(w)
@w
Discovered by Rumelhart, Hinton, and Williams (1986)
5
extremetech.com
21/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Issues
Overfitting
Batch processing
Back-
propagation
Other
architectures
ImageNet
Summary
Other architectures
Convolutional Networks
by LeCun (in Facebook AI Research and NYU)
Biological visual systems
Very widely used in almost every DL problem
Recurrent networks
Sequences (text) and time-series data (speech, weather,
stock price,...)
22/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Issues
Overfitting
Batch processing
Back-
propagation
Other
architectures
ImageNet
Summary
ImageNet competition
6
14M images in 1K categories
Have enabled to test new algorithms in DL
6
Slide from NVIDIA
23/24
Deep Learning
Keunwoo.Choi
@qmul.ac.uk
Introduction
Machine-
Learning
Deep learning
Issues
Summary
Resources
Deeplearning4j tutorials (Korean)
ML lecture in Coursera, Stanford
cs231n from Stanford
24/24

More Related Content

What's hot

Deep Learning for Speech Recognition in Cortana at AI NEXT Conference
Deep Learning for Speech Recognition in Cortana at AI NEXT ConferenceDeep Learning for Speech Recognition in Cortana at AI NEXT Conference
Deep Learning for Speech Recognition in Cortana at AI NEXT ConferenceBill Liu
 
Deep Neural Networks for Multimodal Learning
Deep Neural Networks for Multimodal LearningDeep Neural Networks for Multimodal Learning
Deep Neural Networks for Multimodal LearningMarc Bolaños Solà
 
Speaker and Speech Recognition for Secured Smart Home Applications
Speaker and Speech Recognition for Secured Smart Home ApplicationsSpeaker and Speech Recognition for Secured Smart Home Applications
Speaker and Speech Recognition for Secured Smart Home ApplicationsRoger Gomes
 
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...Universitat Politècnica de Catalunya
 
IRJET- Machine Learning and Noise Reduction Techniques for Music Genre Classi...
IRJET- Machine Learning and Noise Reduction Techniques for Music Genre Classi...IRJET- Machine Learning and Noise Reduction Techniques for Music Genre Classi...
IRJET- Machine Learning and Noise Reduction Techniques for Music Genre Classi...IRJET Journal
 
DNN-based frequency component prediction for frequency-domain audio source se...
DNN-based frequency component prediction for frequency-domain audio source se...DNN-based frequency component prediction for frequency-domain audio source se...
DNN-based frequency component prediction for frequency-domain audio source se...Kitamura Laboratory
 
Recurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRURecurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRUananth
 
TypeScript and Deep Learning
TypeScript and Deep LearningTypeScript and Deep Learning
TypeScript and Deep LearningOswald Campesato
 
Deep Learning in Computer Vision
Deep Learning in Computer VisionDeep Learning in Computer Vision
Deep Learning in Computer VisionSungjoon Choi
 
Real-time DSP Implementation of Audio Crosstalk Cancellation using Mixed Unif...
Real-time DSP Implementation of Audio Crosstalk Cancellation using Mixed Unif...Real-time DSP Implementation of Audio Crosstalk Cancellation using Mixed Unif...
Real-time DSP Implementation of Audio Crosstalk Cancellation using Mixed Unif...CSCJournals
 
Performance analysis of the convolutional recurrent neural network on acousti...
Performance analysis of the convolutional recurrent neural network on acousti...Performance analysis of the convolutional recurrent neural network on acousti...
Performance analysis of the convolutional recurrent neural network on acousti...journalBEEI
 
Recurrent neural networks for sequence learning and learning human identity f...
Recurrent neural networks for sequence learning and learning human identity f...Recurrent neural networks for sequence learning and learning human identity f...
Recurrent neural networks for sequence learning and learning human identity f...SungminYou
 
International Journal of Engineering and Science Invention (IJESI)
International Journal of Engineering and Science Invention (IJESI)International Journal of Engineering and Science Invention (IJESI)
International Journal of Engineering and Science Invention (IJESI)inventionjournals
 
Presentation 01
Presentation 01Presentation 01
Presentation 01BiGYaN
 
IRJET- Implementing Musical Instrument Recognition using CNN and SVM
IRJET- Implementing Musical Instrument Recognition using CNN and SVMIRJET- Implementing Musical Instrument Recognition using CNN and SVM
IRJET- Implementing Musical Instrument Recognition using CNN and SVMIRJET Journal
 
Naver learning to rank question answer pairs using hrde-ltc
Naver learning to rank question answer pairs using hrde-ltcNaver learning to rank question answer pairs using hrde-ltc
Naver learning to rank question answer pairs using hrde-ltcNAVER Engineering
 
Image Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyImage Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyNUPUR YADAV
 
Supervised sequence labelling with recurrent neural networks ch1 6
Supervised sequence labelling with recurrent neural networks ch1 6Supervised sequence labelling with recurrent neural networks ch1 6
Supervised sequence labelling with recurrent neural networks ch1 6SungminYou
 

What's hot (20)

Deep Learning for Speech Recognition in Cortana at AI NEXT Conference
Deep Learning for Speech Recognition in Cortana at AI NEXT ConferenceDeep Learning for Speech Recognition in Cortana at AI NEXT Conference
Deep Learning for Speech Recognition in Cortana at AI NEXT Conference
 
Deep Neural Networks for Multimodal Learning
Deep Neural Networks for Multimodal LearningDeep Neural Networks for Multimodal Learning
Deep Neural Networks for Multimodal Learning
 
Speaker and Speech Recognition for Secured Smart Home Applications
Speaker and Speech Recognition for Secured Smart Home ApplicationsSpeaker and Speech Recognition for Secured Smart Home Applications
Speaker and Speech Recognition for Secured Smart Home Applications
 
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
End-to-end Speech Recognition with Recurrent Neural Networks (D3L6 Deep Learn...
 
FYP presentation
FYP presentationFYP presentation
FYP presentation
 
IRJET- Machine Learning and Noise Reduction Techniques for Music Genre Classi...
IRJET- Machine Learning and Noise Reduction Techniques for Music Genre Classi...IRJET- Machine Learning and Noise Reduction Techniques for Music Genre Classi...
IRJET- Machine Learning and Noise Reduction Techniques for Music Genre Classi...
 
Text categorization
Text categorizationText categorization
Text categorization
 
DNN-based frequency component prediction for frequency-domain audio source se...
DNN-based frequency component prediction for frequency-domain audio source se...DNN-based frequency component prediction for frequency-domain audio source se...
DNN-based frequency component prediction for frequency-domain audio source se...
 
Recurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRURecurrent Neural Networks, LSTM and GRU
Recurrent Neural Networks, LSTM and GRU
 
TypeScript and Deep Learning
TypeScript and Deep LearningTypeScript and Deep Learning
TypeScript and Deep Learning
 
Deep Learning in Computer Vision
Deep Learning in Computer VisionDeep Learning in Computer Vision
Deep Learning in Computer Vision
 
Real-time DSP Implementation of Audio Crosstalk Cancellation using Mixed Unif...
Real-time DSP Implementation of Audio Crosstalk Cancellation using Mixed Unif...Real-time DSP Implementation of Audio Crosstalk Cancellation using Mixed Unif...
Real-time DSP Implementation of Audio Crosstalk Cancellation using Mixed Unif...
 
Performance analysis of the convolutional recurrent neural network on acousti...
Performance analysis of the convolutional recurrent neural network on acousti...Performance analysis of the convolutional recurrent neural network on acousti...
Performance analysis of the convolutional recurrent neural network on acousti...
 
Recurrent neural networks for sequence learning and learning human identity f...
Recurrent neural networks for sequence learning and learning human identity f...Recurrent neural networks for sequence learning and learning human identity f...
Recurrent neural networks for sequence learning and learning human identity f...
 
International Journal of Engineering and Science Invention (IJESI)
International Journal of Engineering and Science Invention (IJESI)International Journal of Engineering and Science Invention (IJESI)
International Journal of Engineering and Science Invention (IJESI)
 
Presentation 01
Presentation 01Presentation 01
Presentation 01
 
IRJET- Implementing Musical Instrument Recognition using CNN and SVM
IRJET- Implementing Musical Instrument Recognition using CNN and SVMIRJET- Implementing Musical Instrument Recognition using CNN and SVM
IRJET- Implementing Musical Instrument Recognition using CNN and SVM
 
Naver learning to rank question answer pairs using hrde-ltc
Naver learning to rank question answer pairs using hrde-ltcNaver learning to rank question answer pairs using hrde-ltc
Naver learning to rank question answer pairs using hrde-ltc
 
Image Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A surveyImage Segmentation Using Deep Learning : A survey
Image Segmentation Using Deep Learning : A survey
 
Supervised sequence labelling with recurrent neural networks ch1 6
Supervised sequence labelling with recurrent neural networks ch1 6Supervised sequence labelling with recurrent neural networks ch1 6
Supervised sequence labelling with recurrent neural networks ch1 6
 

Similar to 딥러닝 개요 (2015-05-09 KISTEP)

Learning Globally-Consistent Local Distance Functions for Shape ...
Learning Globally-Consistent Local Distance Functions for Shape ...Learning Globally-Consistent Local Distance Functions for Shape ...
Learning Globally-Consistent Local Distance Functions for Shape ...butest
 
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...Universitat Politècnica de Catalunya
 
Weight watcher Bay Area ACM Feb 28, 2022
Weight watcher Bay Area ACM Feb 28, 2022 Weight watcher Bay Area ACM Feb 28, 2022
Weight watcher Bay Area ACM Feb 28, 2022 Charles Martin
 
Objective Evaluation of a Deep Neural Network Approach for Single-Channel Spe...
Objective Evaluation of a Deep Neural Network Approach for Single-Channel Spe...Objective Evaluation of a Deep Neural Network Approach for Single-Channel Spe...
Objective Evaluation of a Deep Neural Network Approach for Single-Channel Spe...csandit
 
Deep Learning And Business Models (VNITC 2015-09-13)
Deep Learning And Business Models (VNITC 2015-09-13)Deep Learning And Business Models (VNITC 2015-09-13)
Deep Learning And Business Models (VNITC 2015-09-13)Ha Phuong
 
Stanford ICME Lecture on Why Deep Learning Works
Stanford ICME Lecture on Why Deep Learning WorksStanford ICME Lecture on Why Deep Learning Works
Stanford ICME Lecture on Why Deep Learning WorksCharles Martin
 
introduction to DL network deep learning.ppt
introduction to DL network deep learning.pptintroduction to DL network deep learning.ppt
introduction to DL network deep learning.pptQuangMinhHuynh
 
introduction to deep Learning with full detail
introduction to deep Learning with full detailintroduction to deep Learning with full detail
introduction to deep Learning with full detailsonykhan3
 
Deep Learning for Personalized Search and Recommender Systems
Deep Learning for Personalized Search and Recommender SystemsDeep Learning for Personalized Search and Recommender Systems
Deep Learning for Personalized Search and Recommender SystemsBenjamin Le
 
This Week in Machine Learning and AI Feb 2019
This Week in Machine Learning and AI Feb 2019This Week in Machine Learning and AI Feb 2019
This Week in Machine Learning and AI Feb 2019Charles Martin
 
iccv2009 tutorial: boosting and random forest - part II
iccv2009 tutorial: boosting and random forest - part IIiccv2009 tutorial: boosting and random forest - part II
iccv2009 tutorial: boosting and random forest - part IIzukun
 
Chap 8. Optimization for training deep models
Chap 8. Optimization for training deep modelsChap 8. Optimization for training deep models
Chap 8. Optimization for training deep modelsYoung-Geun Choi
 
EssentialsOfMachineLearning.pdf
EssentialsOfMachineLearning.pdfEssentialsOfMachineLearning.pdf
EssentialsOfMachineLearning.pdfAnkita Tiwari
 
Una introducción a la minería de series temporales
Una introducción a la minería de series temporalesUna introducción a la minería de series temporales
Una introducción a la minería de series temporalesFacultad de Informática UCM
 

Similar to 딥러닝 개요 (2015-05-09 KISTEP) (20)

Perceptrons (D1L2 2017 UPC Deep Learning for Computer Vision)
Perceptrons (D1L2 2017 UPC Deep Learning for Computer Vision)Perceptrons (D1L2 2017 UPC Deep Learning for Computer Vision)
Perceptrons (D1L2 2017 UPC Deep Learning for Computer Vision)
 
Learning Globally-Consistent Local Distance Functions for Shape ...
Learning Globally-Consistent Local Distance Functions for Shape ...Learning Globally-Consistent Local Distance Functions for Shape ...
Learning Globally-Consistent Local Distance Functions for Shape ...
 
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
Multilayer Perceptron (DLAI D1L2 2017 UPC Deep Learning for Artificial Intell...
 
Weight watcher Bay Area ACM Feb 28, 2022
Weight watcher Bay Area ACM Feb 28, 2022 Weight watcher Bay Area ACM Feb 28, 2022
Weight watcher Bay Area ACM Feb 28, 2022
 
Lecture 1.pptx
Lecture 1.pptxLecture 1.pptx
Lecture 1.pptx
 
Objective Evaluation of a Deep Neural Network Approach for Single-Channel Spe...
Objective Evaluation of a Deep Neural Network Approach for Single-Channel Spe...Objective Evaluation of a Deep Neural Network Approach for Single-Channel Spe...
Objective Evaluation of a Deep Neural Network Approach for Single-Channel Spe...
 
Deep Learning And Business Models (VNITC 2015-09-13)
Deep Learning And Business Models (VNITC 2015-09-13)Deep Learning And Business Models (VNITC 2015-09-13)
Deep Learning And Business Models (VNITC 2015-09-13)
 
Stanford ICME Lecture on Why Deep Learning Works
Stanford ICME Lecture on Why Deep Learning WorksStanford ICME Lecture on Why Deep Learning Works
Stanford ICME Lecture on Why Deep Learning Works
 
introduction to DL network deep learning.ppt
introduction to DL network deep learning.pptintroduction to DL network deep learning.ppt
introduction to DL network deep learning.ppt
 
introduction to deep Learning with full detail
introduction to deep Learning with full detailintroduction to deep Learning with full detail
introduction to deep Learning with full detail
 
Deep Learning for Personalized Search and Recommender Systems
Deep Learning for Personalized Search and Recommender SystemsDeep Learning for Personalized Search and Recommender Systems
Deep Learning for Personalized Search and Recommender Systems
 
This Week in Machine Learning and AI Feb 2019
This Week in Machine Learning and AI Feb 2019This Week in Machine Learning and AI Feb 2019
This Week in Machine Learning and AI Feb 2019
 
ENS Macrh 2022.pdf
ENS Macrh 2022.pdfENS Macrh 2022.pdf
ENS Macrh 2022.pdf
 
iccv2009 tutorial: boosting and random forest - part II
iccv2009 tutorial: boosting and random forest - part IIiccv2009 tutorial: boosting and random forest - part II
iccv2009 tutorial: boosting and random forest - part II
 
Mc td
Mc tdMc td
Mc td
 
Chap 8. Optimization for training deep models
Chap 8. Optimization for training deep modelsChap 8. Optimization for training deep models
Chap 8. Optimization for training deep models
 
EssentialsOfMachineLearning.pdf
EssentialsOfMachineLearning.pdfEssentialsOfMachineLearning.pdf
EssentialsOfMachineLearning.pdf
 
Euro-CAT Ergonomic Evaluation
Euro-CAT Ergonomic EvaluationEuro-CAT Ergonomic Evaluation
Euro-CAT Ergonomic Evaluation
 
Unit v transfer learning
Unit v transfer  learningUnit v transfer  learning
Unit v transfer learning
 
Una introducción a la minería de series temporales
Una introducción a la minería de series temporalesUna introducción a la minería de series temporales
Una introducción a la minería de series temporales
 

More from Keunwoo Choi

"All you need is AI and music" by Keunwoo Choi
"All you need is AI and music" by Keunwoo Choi"All you need is AI and music" by Keunwoo Choi
"All you need is AI and music" by Keunwoo ChoiKeunwoo Choi
 
인공지능의 음악 인지 모델 - 65차 한국음악지각인지학회 기조강연 (최근우 박사)
인공지능의 음악 인지 모델 - 65차 한국음악지각인지학회 기조강연 (최근우 박사)인공지능의 음악 인지 모델 - 65차 한국음악지각인지학회 기조강연 (최근우 박사)
인공지능의 음악 인지 모델 - 65차 한국음악지각인지학회 기조강연 (최근우 박사)Keunwoo Choi
 
가상현실을 위한 오디오 기술
가상현실을 위한 오디오 기술가상현실을 위한 오디오 기술
가상현실을 위한 오디오 기술Keunwoo Choi
 
Conditional generative model for audio
Conditional generative model for audioConditional generative model for audio
Conditional generative model for audioKeunwoo Choi
 
Deep Learning with Audio Signals: Prepare, Process, Design, Expect
Deep Learning with Audio Signals: Prepare, Process, Design, ExpectDeep Learning with Audio Signals: Prepare, Process, Design, Expect
Deep Learning with Audio Signals: Prepare, Process, Design, ExpectKeunwoo Choi
 
Convolutional recurrent neural networks for music classification
Convolutional recurrent neural networks for music classificationConvolutional recurrent neural networks for music classification
Convolutional recurrent neural networks for music classificationKeunwoo Choi
 
The effects of noisy labels on deep convolutional neural networks for music t...
The effects of noisy labels on deep convolutional neural networks for music t...The effects of noisy labels on deep convolutional neural networks for music t...
The effects of noisy labels on deep convolutional neural networks for music t...Keunwoo Choi
 
dl4mir tutorial at ETRI, Korea
dl4mir tutorial at ETRI, Koreadl4mir tutorial at ETRI, Korea
dl4mir tutorial at ETRI, KoreaKeunwoo Choi
 
Deep learning for music classification, 2016-05-24
Deep learning for music classification, 2016-05-24Deep learning for music classification, 2016-05-24
Deep learning for music classification, 2016-05-24Keunwoo Choi
 
Understanding Music Playlists
Understanding Music PlaylistsUnderstanding Music Playlists
Understanding Music PlaylistsKeunwoo Choi
 

More from Keunwoo Choi (10)

"All you need is AI and music" by Keunwoo Choi
"All you need is AI and music" by Keunwoo Choi"All you need is AI and music" by Keunwoo Choi
"All you need is AI and music" by Keunwoo Choi
 
인공지능의 음악 인지 모델 - 65차 한국음악지각인지학회 기조강연 (최근우 박사)
인공지능의 음악 인지 모델 - 65차 한국음악지각인지학회 기조강연 (최근우 박사)인공지능의 음악 인지 모델 - 65차 한국음악지각인지학회 기조강연 (최근우 박사)
인공지능의 음악 인지 모델 - 65차 한국음악지각인지학회 기조강연 (최근우 박사)
 
가상현실을 위한 오디오 기술
가상현실을 위한 오디오 기술가상현실을 위한 오디오 기술
가상현실을 위한 오디오 기술
 
Conditional generative model for audio
Conditional generative model for audioConditional generative model for audio
Conditional generative model for audio
 
Deep Learning with Audio Signals: Prepare, Process, Design, Expect
Deep Learning with Audio Signals: Prepare, Process, Design, ExpectDeep Learning with Audio Signals: Prepare, Process, Design, Expect
Deep Learning with Audio Signals: Prepare, Process, Design, Expect
 
Convolutional recurrent neural networks for music classification
Convolutional recurrent neural networks for music classificationConvolutional recurrent neural networks for music classification
Convolutional recurrent neural networks for music classification
 
The effects of noisy labels on deep convolutional neural networks for music t...
The effects of noisy labels on deep convolutional neural networks for music t...The effects of noisy labels on deep convolutional neural networks for music t...
The effects of noisy labels on deep convolutional neural networks for music t...
 
dl4mir tutorial at ETRI, Korea
dl4mir tutorial at ETRI, Koreadl4mir tutorial at ETRI, Korea
dl4mir tutorial at ETRI, Korea
 
Deep learning for music classification, 2016-05-24
Deep learning for music classification, 2016-05-24Deep learning for music classification, 2016-05-24
Deep learning for music classification, 2016-05-24
 
Understanding Music Playlists
Understanding Music PlaylistsUnderstanding Music Playlists
Understanding Music Playlists
 

Recently uploaded

Introduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptxIntroduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptxk795866
 
Correctly Loading Incremental Data at Scale
Correctly Loading Incremental Data at ScaleCorrectly Loading Incremental Data at Scale
Correctly Loading Incremental Data at ScaleAlluxio, Inc.
 
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETEINFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETEroselinkalist12
 
Risk Assessment For Installation of Drainage Pipes.pdf
Risk Assessment For Installation of Drainage Pipes.pdfRisk Assessment For Installation of Drainage Pipes.pdf
Risk Assessment For Installation of Drainage Pipes.pdfROCENODodongVILLACER
 
Application of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptxApplication of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptx959SahilShah
 
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdfCCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdfAsst.prof M.Gokilavani
 
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdfCCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdfAsst.prof M.Gokilavani
 
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...srsj9000
 
An introduction to Semiconductor and its types.pptx
An introduction to Semiconductor and its types.pptxAn introduction to Semiconductor and its types.pptx
An introduction to Semiconductor and its types.pptxPurva Nikam
 
Comparative Analysis of Text Summarization Techniques
Comparative Analysis of Text Summarization TechniquesComparative Analysis of Text Summarization Techniques
Comparative Analysis of Text Summarization Techniquesugginaramesh
 
Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...VICTOR MAESTRE RAMIREZ
 
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerStudy on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerAnamika Sarkar
 
Work Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvvWork Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvvLewisJB
 
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxDecoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxJoão Esperancinha
 
complete construction, environmental and economics information of biomass com...
complete construction, environmental and economics information of biomass com...complete construction, environmental and economics information of biomass com...
complete construction, environmental and economics information of biomass com...asadnawaz62
 
Electronically Controlled suspensions system .pdf
Electronically Controlled suspensions system .pdfElectronically Controlled suspensions system .pdf
Electronically Controlled suspensions system .pdfme23b1001
 
Why does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsync
Why does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsyncWhy does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsync
Why does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsyncssuser2ae721
 
main PPT.pptx of girls hostel security using rfid
main PPT.pptx of girls hostel security using rfidmain PPT.pptx of girls hostel security using rfid
main PPT.pptx of girls hostel security using rfidNikhilNagaraju
 
Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024hassan khalil
 

Recently uploaded (20)

Introduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptxIntroduction-To-Agricultural-Surveillance-Rover.pptx
Introduction-To-Agricultural-Surveillance-Rover.pptx
 
Correctly Loading Incremental Data at Scale
Correctly Loading Incremental Data at ScaleCorrectly Loading Incremental Data at Scale
Correctly Loading Incremental Data at Scale
 
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETEINFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
INFLUENCE OF NANOSILICA ON THE PROPERTIES OF CONCRETE
 
Risk Assessment For Installation of Drainage Pipes.pdf
Risk Assessment For Installation of Drainage Pipes.pdfRisk Assessment For Installation of Drainage Pipes.pdf
Risk Assessment For Installation of Drainage Pipes.pdf
 
Application of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptxApplication of Residue Theorem to evaluate real integrations.pptx
Application of Residue Theorem to evaluate real integrations.pptx
 
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdfCCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
 
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdfCCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
CCS355 Neural Networks & Deep Learning Unit 1 PDF notes with Question bank .pdf
 
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
 
young call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Service
young call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Serviceyoung call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Service
young call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Service
 
An introduction to Semiconductor and its types.pptx
An introduction to Semiconductor and its types.pptxAn introduction to Semiconductor and its types.pptx
An introduction to Semiconductor and its types.pptx
 
Comparative Analysis of Text Summarization Techniques
Comparative Analysis of Text Summarization TechniquesComparative Analysis of Text Summarization Techniques
Comparative Analysis of Text Summarization Techniques
 
Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...
 
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube ExchangerStudy on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
Study on Air-Water & Water-Water Heat Exchange in a Finned Tube Exchanger
 
Work Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvvWork Experience-Dalton Park.pptxfvvvvvvv
Work Experience-Dalton Park.pptxfvvvvvvv
 
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxDecoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
 
complete construction, environmental and economics information of biomass com...
complete construction, environmental and economics information of biomass com...complete construction, environmental and economics information of biomass com...
complete construction, environmental and economics information of biomass com...
 
Electronically Controlled suspensions system .pdf
Electronically Controlled suspensions system .pdfElectronically Controlled suspensions system .pdf
Electronically Controlled suspensions system .pdf
 
Why does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsync
Why does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsyncWhy does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsync
Why does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsync
 
main PPT.pptx of girls hostel security using rfid
main PPT.pptx of girls hostel security using rfidmain PPT.pptx of girls hostel security using rfid
main PPT.pptx of girls hostel security using rfid
 
Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024
 

딥러닝 개요 (2015-05-09 KISTEP)