Clockwork Convnets for Video Semantic Segmentation.
Adaptive video processing by incorporating data-driven clocks.
We define a novel family of "clockwork" convnets driven by fixed or adaptive clock signals that schedule the processing of different layers at different update rates according to their semantic stability. We design a pipeline schedule to reduce latency for real-time recognition and a fixed-rate schedule to reduce overall computation. Finally, we extend clockwork scheduling to adaptive video processing by incorporating data-driven clocks that can be tuned on unlabeled video.
https://arxiv.org/pdf/1608.03609v1.pdf
https://github.com/shelhamer/clockwork-fcn
http://www.gitxiv.com/posts/89zR7ATtd729JEJAg/clockwork-convnets-for-video-semantic-segmentation
#Caffe #video #Segmentation
Adaptive video processing by incorporating data-driven clocks.
We define a novel family of "clockwork" convnets driven by fixed or adaptive clock signals that schedule the processing of different layers at different update rates according to their semantic stability. We design a pipeline schedule to reduce latency for real-time recognition and a fixed-rate schedule to reduce overall computation. Finally, we extend clockwork scheduling to adaptive video processing by incorporating data-driven clocks that can be tuned on unlabeled video.
https://arxiv.org/pdf/1608.03609v1.pdf
https://github.com/shelhamer/clockwork-fcn
http://www.gitxiv.com/posts/89zR7ATtd729JEJAg/clockwork-convnets-for-video-semantic-segmentation
#Caffe #video #Segmentation
Multifaceted Feature Visualization.
Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks.
We can better understand deep neural networks by identifying which features each of their neurons have learned to detect. Here, we introduce an algorithm that explicitly uncovers the multiple facets of each neuron by producing a synthetic visualization of each of the types of images that activate a neuron. We also introduce regularization methods that produce state-of-the-art results in terms of the interpretability of images obtained by activation maximization.
https://github.com/Evolving-AI-Lab/mfv
https://arxiv.org/pdf/1602.03616v2.pdf
http://www.gitxiv.com/posts/Kqy2rHju5EsqpC32N/multifaceted-feature-visualization
Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks.
We can better understand deep neural networks by identifying which features each of their neurons have learned to detect. Here, we introduce an algorithm that explicitly uncovers the multiple facets of each neuron by producing a synthetic visualization of each of the types of images that activate a neuron. We also introduce regularization methods that produce state-of-the-art results in terms of the interpretability of images obtained by activation maximization.
https://github.com/Evolving-AI-Lab/mfv
https://arxiv.org/pdf/1602.03616v2.pdf
http://www.gitxiv.com/posts/Kqy2rHju5EsqpC32N/multifaceted-feature-visualization
Запись и презентация с вводного вебинара по DeepLearning от Александра Гончар для студентов СФ БашГУ.
https://www.youtube.com/watch?v=8pbQ9Pve8bo
https://www.linkedin.com/in/alex-honchar-4423b962
https://www.youtube.com/watch?v=8pbQ9Pve8bo
https://www.linkedin.com/in/alex-honchar-4423b962
Когда мы сможем загрузить мозг в компьютер
Специалист по машинному обучению, создатель одной из сильнейших шахматных программ Сергей Марков прочитал в Москве лекцию о перспективах перемещения сознания на другой носитель. О прогрессе в области нейроинтерфейсов, первых киборгах и перспективах нейронных сетей — в материале «Футуриста».
http://futurist.ru/articles/558
Специалист по машинному обучению, создатель одной из сильнейших шахматных программ Сергей Марков прочитал в Москве лекцию о перспективах перемещения сознания на другой носитель. О прогрессе в области нейроинтерфейсов, первых киборгах и перспективах нейронных сетей — в материале «Футуриста».
http://futurist.ru/articles/558
LipNet: Automated lipreading - Чтение по губам.
93% распознавание сетью (люди 52%)
Lipreading is the task of decoding text from the movement of a speaker’s mouth. Traditional approaches separated the problem into two stages: designing or learning visual features, and prediction.
http://www.oxml.co.uk/publications/2016-Assael_Shillingford_LipNet.pdf
https://www.youtube.com/watch?v=fa5QGremQf8
93% распознавание сетью (люди 52%)
Lipreading is the task of decoding text from the movement of a speaker’s mouth. Traditional approaches separated the problem into two stages: designing or learning visual features, and prediction.
http://www.oxml.co.uk/publications/2016-Assael_Shillingford_LipNet.pdf
https://www.youtube.com/watch?v=fa5QGremQf8
Команда Google DeepMind представила новый ИИ, способный самостоятельно учиться выполнять задачи
https://tproger.ru/news/deepmind-new-algorithm/
https://tproger.ru/news/deepmind-new-algorithm/
Port of Single Shot MultiBox Detector to Keras (SSD)
https://arxiv.org/pdf/1512.02325v3.pdf
https://github.com/rykov8/ssd_keras
#keras #ssd
https://arxiv.org/pdf/1512.02325v3.pdf
https://github.com/rykov8/ssd_keras
#keras #ssd
Курс по Tensorflow от BigDataUniversity (free)
https://bigdatauniversity.com/courses/deep-learning-tensorflow/
ML0120EN
COURSE LEVEL: Advanced
TIME TO COMPLETE: 10 Hours
#tensorflow
https://bigdatauniversity.com/courses/deep-learning-tensorflow/
ML0120EN
COURSE LEVEL: Advanced
TIME TO COMPLETE: 10 Hours
#tensorflow