<![CDATA[Deep Learning 2018/2019 (SD 640)]]>
http://www.video.uni-erlangen.de
en2019 FAUTue, 29 Jan 2019 00:00:00 +0100https://cdn.video.uni-erlangen.de/Images/Maier_1400_thumb.png<![CDATA[Deep Learning 2018/2019 (SD 640)]]>
http://www.video.uni-erlangen.de
Prof. Dr. Andreas MaierDeep 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, ...)
FAUitunes@uni-erlangen.deUni-Erlangen, FAU,arbitrary, bernoulli, reconstruction, deep, visualization, backpropagation, inception, block, unsupervised, label, pattern, DeepDream, Go, Detection, Siri, Alexa, machine, neuronal, multi-layer, abstractionno<![CDATA[1 - Deep Learning 2018/2019]]>01:27:00/data/2018/10/16/FAU_W18_DL_ClipID_9548/20181016-DL-Maier-OC-640x360.m4vTue, 16 Oct 2018 00:00:00 +0200Prof. Dr. Andreas MaierDeepDream, Go, Detection, Siri, Alexa, machine, neuronal, pattern, perceptron, learning, network, recognitionDeep 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, ...)
1<![CDATA[2 - Deep Learning 2018/2019]]>01:24:57/data/2018/10/23/FAU_W18_DL_ClipID_9595/20181023-DL-Maier-OC-640x360.m4vTue, 23 Oct 2018 00:00:00 +0200Prof. Dr. Andreas Maiermulti-layer, abstraction, layer, softmax, decision, feedback, activation, perceptron, problem, output, example, perceptron, neural, network, layer, activation, networks, learning, layers, neural, function, ravikumar, analytic, loss, breininger, propagation, input, forward, universal, gradient, functionsDeep 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, ...)
2<![CDATA[3 - Deep Learning 2018/2019]]>01:38:06/data/2018/10/30/FAU_W18_DL_ClipID_9631/20181030-DL-Maier-OC-640x360.m4vTue, 30 Oct 2018 00:00:00 +0100Tobias Würfloptimization, likelihood, momentum, Nesterov, adam, possible, entropy, subgradient, functions, probability, gradients, subgradients, regression, estimation, loss, function, regression, classification, bernoulli, subgradient, gradient, network, classification, functionDeep 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, ...)
3<![CDATA[4 - Deep Learning 2018/2019]]>01:17:15/data/2018/11/06/FAU_W18_DL_ClipID_9679/20181106-DL-Maier-OC-640x360.m4vTue, 06 Nov 2018 00:00:00 +0100Prof. Dr. Andreas Maiernetworks, learning, neural, convolution, representation, linear, layers, functionDeep 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, ...)
4<![CDATA[5 - Deep Learning 2018/2019]]>01:04:36/data/2018/11/13/FAU_W18_DL_ClipID_9729/20180509-DL-Breininger-OC-640x360.m4vTue, 13 Nov 2018 00:00:00 +0100M. Sc. Katharina BreiningerDeep 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, ...)
5<![CDATA[6 - Deep Learning 2018/2019]]>01:04:15/data/2018/11/20/FAU_W18_DL_ClipID_9736/20181120-DL-Maier-OC-640x360.m4vTue, 20 Nov 2018 00:00:00 +0100Prof. Dr. Andreas Maierpractices, training, data, gradient, performance, function, classification, accuracy, positives, network, multiple, classifiers, measures, model, architecture, comparing, validation, ravikumarDeep 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, ...)
6<![CDATA[7 - Deep Learning 2018/2019]]>01:07:41/data/2018/11/27/FAU_W18_DL_ClipID_9787/20181127-DL-Maier-OC-640x360.m4vTue, 27 Nov 2018 00:00:00 +0100Prof. Dr. Andreas Maiernetwork, layer, kernel, convolution, inception, bottleneck, deep, learning, label-smoothing, regularization, architecture, block, reinforcementDeep 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, ...)
7<![CDATA[8 - Deep Learning 2018/2019]]>01:00:59/data/2018/12/04/FAU_W18_DL_ClipID_9828/20181204-DL-Maier-OC-640x360.m4vTue, 04 Dec 2018 00:00:00 +0100Prof. Dr. Andreas Maierrecurrent, neural, network, RNN, backpropagation, BPTT, long, short, term, gradient, LSTM, GRUDeep 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, ...)
8<![CDATA[9 - Deep Learning 2018/2019]]>01:06:17/data/2018/12/11/FAU_W18_DL_ClipID_9873/20181211-DL-Maier-OC-640x360.m4vTue, 11 Dec 2018 00:00:00 +0100Prof. Dr. Andreas Maiervisualization, network, neural, architecture, backpropagation, inversion, confoundDeep 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, ...)
9<![CDATA[10 - Deep Learning 2018/2019]]>01:07:23/data/2018/12/18/FAU_W18_DL_ClipID_9912/20181218-DL-Maier-OC-640x360.m4vTue, 18 Dec 2018 00:00:00 +0100Prof. Dr. Andreas Maieratari, game, state, networkDeep 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, ...)
10<![CDATA[11 - Deep Learning 2018/2019]]>01:22:46/data/2019/01/08/FAU_W18_DL_ClipID_9958/20190108-DL-Breininger-OC-640x360.m4vTue, 08 Jan 2019 00:00:00 +0100M. Sc. Katharina Breiningerobject, detection, segmentation, region-based, single-shot, upsampling, convolution, network, recognition, localization, classification, label, CNN, network, upsampling, bounding, convolutional, detection, maier, context, prediction, output, stride, semantic, inceptionDeep 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, ...)
11<![CDATA[12 - Deep Learning 2018/2019]]>01:10:56/data/2019/01/22/FAU_W18_DL_ClipID_10049/20190122-DL-Breininger-OC-640x360.m4vTue, 22 Jan 2019 00:00:00 +0100Prof. Dr. Andreas Maierunsupervised, deep, learning, data, functions, control, autoencoder, engine, image, optimal, discriminator, training, ravikumar, unsupervised, generative, networks, model, applicationsDeep 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, ...)
12<![CDATA[13 - Deep Learning 2018/2019]]>01:25:16/data/2019/01/29/FAU_W18_DL_ClipID_10085/20190129-DL-Maier-OC-640x360.m4vTue, 29 Jan 2019 00:00:00 +0100Prof. Dr. Andreas Maierdeep, learning, arbitrary, network, image, proceeding, segmentation, reconstruction, implementation, discretizationDeep 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, ...)
13