Deep Learning - Loss and Optimization Part 2

This video explains hinge loss and its relation to support vector machines. It enables to embed optimization constraints into loss functions.

Further Reading: 
<a href="https://www.sciencedirect.com/science/article/pii/S093938891830120X">A gentle Introduction to Deep Learning</a> 
<a href="https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2019/Zarei19-ULA.pdf">User Loss</a>

Deep Learning - Loss and Optimization Part 2 This video explains hinge loss and its relation to support vector machines. It enables to embed optimization constraints into loss functions. Further Reading: A gentle Introduction to Deep Learning User Loss

Deep Learning - Loss and Optimization Part 2

This video explains hinge loss and its relation to support vector machines. It enables to embed optimization constraints into loss functions.

Further Reading: 
<a href="https://www.sciencedirect.com/science/article/pii/S093938891830120X" rel="noopener noreferrer">A gentle Introduction to Deep Learning</a> 
<a href="https://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2019/Zarei19-ULA.pdf" rel="noopener noreferrer">User Loss</a>

Deep Learning - Loss and Optimization Part 2

Deep Learning (DL) has attracted much interest in a wide range of applications such as image recognition, speech recognition, and artificial intelligence, both from academia and industry. This lecture introduces the core elements of neural networks and deep learning, it comprises:
	<ul>
		<li>
		(multilayer) perceptron, backpropagation, fully connected neural networks
		</li>
		<li>
		loss functions and optimization strategies
		</li>
		<li>
		convolutional neural networks (CNNs)
		</li>
		<li>
		activation functions
		</li>
		<li>
		regularization strategies
		</li>
		<li>
		common practices for training and evaluating neural networks
		</li>
		<li>
		visualization of networks and results
		</li>
		<li>
		common architectures, such as LeNet, Alexnet, VGG, GoogleNet
		</li>
		<li>
		recurrent neural networks (RNN, TBPTT, LSTM, GRU)
		</li>
		<li>
		deep reinforcement learning
		</li>
		<li>
		unsupervised learning (autoencoder, RBM, DBM, VAE)
		</li>
		<li>
		generative adversarial networks (GANs)
		</li>
		<li>
		weakly supervised learning
		</li>
		<li>
		applications of deep learning (segmentation, object detection, speech recognition, ...)
		</li>
	</ul>

	The accompanying exercises will provide a deeper understanding of the workings and architecture of neural networks.

Education

Deep Learning (DL) has attracted much interest in a wide range of applications such as image recognition, speech recognition, and artificial intelligence, both from academia and industry. This lecture introduces the core elements of neural networks and deep learning, it comprises: (multilayer) perceptron, backpropagation, fully connected neural networks loss functions and optimization strategies convolutional neural networks (CNNs) activation functions regularization strategies common practices for training and evaluating neural networks visualization of networks and results common architectures, such as LeNet, Alexnet, VGG, GoogleNet recurrent neural networks (RNN, TBPTT, LSTM, GRU) deep reinforcement learning unsupervised learning (autoencoder, RBM, DBM, VAE) generative adversarial networks (GANs) weakly supervised learning applications of deep learning (segmentation, object detection, speech recognition, ...) The accompanying exercises will provide a deeper understanding of the workings and architecture of neural networks.

&nbsp;


	Deep Learning (DL) has attracted much interest in a wide range of applications such as image recognition, speech recognition, and artificial intelligence, both from academia and industry. This lecture introduces the core elements of neural networks and deep learning, it comprises:
	<ul>
		<li>
		(multilayer) perceptron, backpropagation, fully connected neural networks
		</li>
		<li>
		loss functions and optimization strategies
		</li>
		<li>
		convolutional neural networks (CNNs)
		</li>
		<li>
		activation functions
		</li>
		<li>
		regularization strategies
		</li>
		<li>
		common practices for training and evaluating neural networks
		</li>
		<li>
		visualization of networks and results
		</li>
		<li>
		common architectures, such as LeNet, Alexnet, VGG, GoogleNet
		</li>
		<li>
		recurrent neural networks (RNN, TBPTT, LSTM, GRU)
		</li>
		<li>
		deep reinforcement learning
		</li>
		<li>
		unsupervised learning (autoencoder, RBM, DBM, VAE)
		</li>
		<li>
		generative adversarial networks (GANs)
		</li>
		<li>
		weakly supervised learning
		</li>
		<li>
		applications of deep learning (segmentation, object detection, speech recognition, ...)
		</li>
	</ul>

	The accompanying exercises will provide a deeper understanding of the workings and architecture of neural networks.
	


&nbsp;

Share Deep Learning - Loss and Optimization Part 2

Sign up to save your podcasts

Deep Learning - Loss and Optimization Part 2

Deep Learning - Loss and Optimization Part 2

More shows like Deep Learning - Plain Version

Public Theology - Religion - Education. Interreligious Perspectives

Lineare Algebra I

Foundations of Quantum Mechanics

Die deutsche Königswahl (1125-1411)

Lectures on Quantum Theory (Elite Graduate Programme) 2015 -Measurements

Einführungsvorlesung Mittelalter

Lectures on the Geometric Anatomy of Theoretical Physics

Quantum Computing

Modern Optics 3: Quantum Optics