NEURAL NETWORK AND DEEP

LEARNING

Diapositivas extraídas de
DeepLearning.ai
https://www.youtube.com/playlist?list=PLkDaE6sCZn6Ec-XTbcX1uRg2_u4xOEky0
Supervised Learning
Neural Network
Neural Network
Neural Network Examples
 Neural Network
Most deep learning methods use neural network architectures, which is why deep
learning models are often referred to as deep neural networks.

The term “deep” usually refers to the number of hidden layers in the neural network.
Traditional neural networks only contain 2-3 hidden layers, while deep networks can have
as many as 150.

Deep learning models are trained by using large sets of labeled data and neural network
architectures that learn features directly from the data without the need for manual
feature extraction.
 Neural Network
One of the most popular types of deep neural networks is known as convolutional neural
networks (CNN or ConvNet). A CNN convolves learned features with input data, and
uses 2D convolutional layers, making this architecture well suited to processing 2D data,
such as images.

CNNs eliminate the need for manual feature extraction, so you do not need to identify
features used to classify images. The CNN works by extracting features directly from images.
The relevant features are not pretrained; they are learned while the network trains on a
collection of images. This automated feature extraction makes deep learning models highly
accurate for computer vision tasks such as object classification.
Neural Network
Difference Machine Learning and Deep
Learning
Why is deep Learning taking off??
Deep Learning in Computer vision
Edge Detection Examples
Vertical edge Detector
Convolution network ConvNet
Example Convolution network
 Example Digit detection
• https://www.youtube.com/watch?v=oI2rvjbzV
mI
 State of Computer Vision
La detección de objetos en imágenes implica, no solamente identificar de que
tipo de objeto se trata, sino también localizarlo dentro de la imagen (obtener las
coordenadas de la “caja” que lo contiene). En otras palabras,
detección = clasificación + localización.
Classification with localization
Classification with localization
Target label Y
Object detection
Object detection
Evaluating Object localization
Intersection over union
Overlapping objects: Anchor boxes
Overlapping objects: Anchor boxes
Non-Max suppression
Non-Max suppression
Review of Deep Learning Algorithms
for Object Detection
 R-CCN
• Region-CNN (R-CNN) is one of the state-of-the-art CNN-based deep learning object
detection approaches. Based on this, there are fast R-CNN and faster R-CNN for faster speed
object detection.
- It takes a huge amount of time to train the network as you would have to classify 2000
region proposals per image
- It cannot be implemented in real time as it takes around 47 seconds for each test image.
- The selective search algorithm is a fixed algorithm. Therefore, no learning is happening
- at that stage. This could lead to the generation of bad candidate region proposals.
Fast R-CNN
YOLO -training
YOLO -training
YOLO