Distributed deep rl on spark strata singaporeAdam Gibson
This talk briefly covers deep reinforcemeent learning on spark and the benefits of using large scale commodity compute with gpus for ease of running simulations as well as distributed training for use cases that aren't games such as network intrusion and risk. This talk also briefly mentions rl4j and our work with openai gym.
Distributed deep rl on spark strata singaporeAdam Gibson
This talk briefly covers deep reinforcemeent learning on spark and the benefits of using large scale commodity compute with gpus for ease of running simulations as well as distributed training for use cases that aren't games such as network intrusion and risk. This talk also briefly mentions rl4j and our work with openai gym.
This talk was on deep learning use cases outside of computer vision. It also covered larger scale patterns of what good deep learning use cases typically look like. We end up on an explanation of anomaly detection and various kinds of anomaly use cases.
https://imatge-upc.github.io/activitynet-2016-cvprw/
This thesis explore different approaches using Convolutional and Recurrent Neural Networks to classify and temporally localize activities on videos, furthermore an implementation to achieve it has been proposed. As the first step, features have been extracted from video frames using an state of the art 3D Convolutional Neural Network. This features are fed in a recurrent neural network that solves the activity classification and temporally location tasks in a simple and flexible way. Different architectures and configurations have been tested in order to achieve the best performance and learning of the video dataset provided. In addition it has been studied different kind of post processing over the trained network's output to achieve a better results on the temporally localization of activities on the videos. The results provided by the neural network developed in this thesis have been submitted to the ActivityNet Challenge 2016 of the CVPR, achieving competitive results using a simple and flexible architecture.
Deep learning in production with the bestAdam Gibson
Getting deep learning adopted at your company. The current landscape of academia vs industry. Presentation at AI with the best (online conference):
http://ai.withthebest.com/
Strata Beijing - Deep Learning in Production on SparkAdam Gibson
Recent talk at strata beijing - half english half chinese covering use cases of deep learning, deep learning in production and the different components of deeplearning4j.
"Earthsoft Foundation of Guidance (EFG) is working as an NGO/NPO for students - Education & Career guidance and for Professionals for soft skills enhancements. We are working speading , sharing knowledge; experience globally.It has uploaded important presentations at http://myefg.in/downloads.aspx. Also visit www.slideshare.net and search using key word - earthsoft Read http://tl.gd/jm1gh5 and view picture http://twitpic.com/cept60 http://www.slideshare.net/rrakhecha/efg-activities-of-one-year27-mar2013 Be mentor using your education, knowledge & experience to contribute for a social cause & do conduct free training/ workshop seeking help of existing platforms Kindly spread to your friends.Thank you! - Earthsoft Foundation of Guidance
Let us make earth little softer.."
The Problem:
September 11, 2001 proved the High-rise rescue operational inadequacies of municipally based fire/rescue services. It is imperative that this problem is quickly addressed using both existing and proposed technologies and methods.
A Solution:
IN-S.E.R.T. is a dedicated emergency response unit operated as an extension of The United States Coast Guard (USCG) F.E.M.A. and existing fire/rescue departments in any major city. Team members will have at their disposal a range of fire/rescue and fire suppression technologies designed to facilitate High-rise rescue operations. The potential flexibility of IN-S.E.R.T makes it a template for a broad spectrum of emergency responses not limited to High-rise rescue. Therefore, it has value beyond that immediately observable.
Technology, Equipment, Methods:
Specially trained personnel will benefit from the decades old expertise of the acclaimed “Smoke Jumpers” of the Western/Pacific Northwestern United States and Red Adair’s legendary pyro-containment methodologies. Additionally, they will benefit from newly developed Victim Extraction At Altitude (VEAA)techniques.
Resumen de 'The Reading Zone' de Nancie AtwellJosep Oliver
Resumen del libro 'The Reading Zone' de Nancie Atwell para profesores que quieran cambiar su metodología de enseñanza de la literatura hacia un taller de lectura.
This talk was on deep learning use cases outside of computer vision. It also covered larger scale patterns of what good deep learning use cases typically look like. We end up on an explanation of anomaly detection and various kinds of anomaly use cases.
https://imatge-upc.github.io/activitynet-2016-cvprw/
This thesis explore different approaches using Convolutional and Recurrent Neural Networks to classify and temporally localize activities on videos, furthermore an implementation to achieve it has been proposed. As the first step, features have been extracted from video frames using an state of the art 3D Convolutional Neural Network. This features are fed in a recurrent neural network that solves the activity classification and temporally location tasks in a simple and flexible way. Different architectures and configurations have been tested in order to achieve the best performance and learning of the video dataset provided. In addition it has been studied different kind of post processing over the trained network's output to achieve a better results on the temporally localization of activities on the videos. The results provided by the neural network developed in this thesis have been submitted to the ActivityNet Challenge 2016 of the CVPR, achieving competitive results using a simple and flexible architecture.
Deep learning in production with the bestAdam Gibson
Getting deep learning adopted at your company. The current landscape of academia vs industry. Presentation at AI with the best (online conference):
http://ai.withthebest.com/
Strata Beijing - Deep Learning in Production on SparkAdam Gibson
Recent talk at strata beijing - half english half chinese covering use cases of deep learning, deep learning in production and the different components of deeplearning4j.
"Earthsoft Foundation of Guidance (EFG) is working as an NGO/NPO for students - Education & Career guidance and for Professionals for soft skills enhancements. We are working speading , sharing knowledge; experience globally.It has uploaded important presentations at http://myefg.in/downloads.aspx. Also visit www.slideshare.net and search using key word - earthsoft Read http://tl.gd/jm1gh5 and view picture http://twitpic.com/cept60 http://www.slideshare.net/rrakhecha/efg-activities-of-one-year27-mar2013 Be mentor using your education, knowledge & experience to contribute for a social cause & do conduct free training/ workshop seeking help of existing platforms Kindly spread to your friends.Thank you! - Earthsoft Foundation of Guidance
Let us make earth little softer.."
The Problem:
September 11, 2001 proved the High-rise rescue operational inadequacies of municipally based fire/rescue services. It is imperative that this problem is quickly addressed using both existing and proposed technologies and methods.
A Solution:
IN-S.E.R.T. is a dedicated emergency response unit operated as an extension of The United States Coast Guard (USCG) F.E.M.A. and existing fire/rescue departments in any major city. Team members will have at their disposal a range of fire/rescue and fire suppression technologies designed to facilitate High-rise rescue operations. The potential flexibility of IN-S.E.R.T makes it a template for a broad spectrum of emergency responses not limited to High-rise rescue. Therefore, it has value beyond that immediately observable.
Technology, Equipment, Methods:
Specially trained personnel will benefit from the decades old expertise of the acclaimed “Smoke Jumpers” of the Western/Pacific Northwestern United States and Red Adair’s legendary pyro-containment methodologies. Additionally, they will benefit from newly developed Victim Extraction At Altitude (VEAA)techniques.
Resumen de 'The Reading Zone' de Nancie AtwellJosep Oliver
Resumen del libro 'The Reading Zone' de Nancie Atwell para profesores que quieran cambiar su metodología de enseñanza de la literatura hacia un taller de lectura.
Deploying signature verification with deep learningAdam Gibson
Presentation covered building a signature verification system and deploying it to production. This includes resources usage as well as how the model was picked.
Meetup held in Tokyo with Deep learning Otemachi.
Self driving computers active learning workflows with human interpretable ve...Adam Gibson
Human in the loop learning workflows leveraging deep learning to group and cluster data. Also, techniques for accounting for machine learning failures.
Anomaly Detection and Automatic Labeling with Deep LearningAdam Gibson
Adam Gibson demonstrates how to use variational autoencoders to automatically label time series location data. You'll explore the challenge of imbalanced classes and anomaly detection, learn how to leverage deep learning for automatically labeling (and the pitfalls of this), and discover how you can deploy these techniques in your organization.
Recent presentation on deeplearning4j's new features as well as some underused features of the AI framework like arbiter,datavec's transform process and libnd4j.
Gave a talk at:
www.meetup.com/SF-Bayarea-Machine-Learning/events/221739934/
Covers basic architecture of a scientific lib and my take on it with nd4j.
These slides accompanied a demo of Deeplearning4j at the SF Data Mining Meetup hosted by Trulia.
http://www.meetup.com/Data-Mining/events/212445872/
Deep-learning is useful in detecting identifying similarities to augment search and text analytics; predicting customer lifetime value and churn; and recognizing faces and voices.
Deeplearning4j is an infinitely scalable deep-learning architecture suitable for Hadoop and other big-data structures. It includes a distributed deep-learning framework and a normal deep-learning framework; i.e. it runs on a single thread as well. Training takes place in the cluster, which means it can process massive amounts of data. Nets are trained in parallel via iterative reduce, and they are equally compatible with Java, Scala and Clojure. The distributed deep-learning framework is made for data input and neural net training at scale, and its output should be highly accurate predictive models.
The framework's neural nets include restricted Boltzmann machines, deep-belief networks, deep autoencoders, convolutional nets and recursive neural tensor networks.
Finally, Deeplearning4j integrates with GPUs. A stable version was released in October.