- Видео 503
- Просмотров 588 939
KDD2016 video
США
Добавлен 24 июн 2016
KDD 2016, a premier interdisciplinary conference, brings together researchers and practitioners from data science, data mining, knowledge discovery, large-scale data analytics, and big data. Started in 1989, KDD is the oldest & largest data mining conference worldwide. We pioneered “Big Data”, “Data Science”, and “Predictive Analytics” solutions before these names existed - some of the first & most highly cited research papers on these topics were published in our conference.
Personalised Recommendations for Modes of Transport: A Sequence-based Approach
Author:
Gunjan Kumar, Insight Centre for Data Analytics
Abstract:
In this paper we consider the problem of recommending modes of transport to users in an urban setting. In particular, we build on our past work in which a general framework for activity recommendation is proposed. To model the personal preferences and habits of users, the framework uses a sequence-based approach to capture the order as well as the context associated with user activity patterns. Here, we extend this work by introducing a machine learning approach to learn and take into account the natural variations in the regularity and repetition of individual user behaviour that occur. We demonstrate the versatility of our ...
Gunjan Kumar, Insight Centre for Data Analytics
Abstract:
In this paper we consider the problem of recommending modes of transport to users in an urban setting. In particular, we build on our past work in which a general framework for activity recommendation is proposed. To model the personal preferences and habits of users, the framework uses a sequence-based approach to capture the order as well as the context associated with user activity patterns. Here, we extend this work by introducing a machine learning approach to learn and take into account the natural variations in the regularity and repetition of individual user behaviour that occur. We demonstrate the versatility of our ...
Просмотров: 246
Видео
Generating Local Explanations of Network Anomalies via Score Decomposition
Просмотров 2228 лет назад
Author: Timothy La Fond, Computer Science Department, Purdue University Abstract: An important application in network analysis is the detection of anomalous events in a network time series. These events could merely be times of interest in the network timeline or they could be examples of malicious activity or network malfunction. Once a set of events are identified by the anomaly detection alg...
Detection of Cyber-Physical Faults and Intrusions from Physical Correlations
Просмотров 2948 лет назад
Author: Andrey Lokhov, Los Alamos National Laboratory More on www.kdd.org/kdd2016/ KDD2016 Conference is published on videolectures.net/
Fast and Accurate Kmeans Clustering with Outliers
Просмотров 2,9 тыс.8 лет назад
Author: Shalmoli Gupta, Department of Computer Science, University of Illinois at Urbana-Champaign More on www.kdd.org/kdd2016/ KDD2016 Conference is published on videolectures.net/
Dealing with Class Imbalance using Thresholding
Просмотров 3,6 тыс.8 лет назад
Author: Rumi Ghosh, Robert Bosch LLC. Abstract: We propose thresholding as an approach to deal with class imbalance. We define the concept of thresholding as a process of determining a decision boundary in the presence of a tunable parameter. The threshold is the maximum value of this tunable parameter where the conditions of a certain decision are satisfied. We show that thresholding is applic...
Beauty and Brains: Detecting Anomalous Pattern Co-Occurrences
Просмотров 2168 лет назад
Author: Roel Bertens, Department of Information and Computing Sciences, Utrecht University More on www.kdd.org/kdd2016/ KDD2016 Conference is published on videolectures.net/
Interpretable Anomaly Detection for Monitoring of High Performance Computing Systems
Просмотров 5218 лет назад
Author: Elisabeth Baseman, Los Alamos National Laboratory More on www.kdd.org/kdd2016/ KDD2016 Conference is published on videolectures.net/
Moving from Anomalies to Known Phenomena
Просмотров 7698 лет назад
Author: Jeff Schneider, School of Computer Science, Carnegie Mellon University Abstract: Basic anomaly detection finds data points that are unusual relative to an expected distribution and there are good methods for defining expected distributions and quantifying deviation from them. However, using anomaly detectors in operational systems has proven to be a challenge. Naive flagging of anomalou...
A Generative Model of Urban Activities from Cellular Data
Просмотров 5938 лет назад
Author: Mogeng Yin, UC Berkeley Abstract: Activity based travel models are the main tools used to evaluate traffic conditions in the context of rapidly changing travel demand. However, data collection for activity based models is performed through travel surveys that are infrequent, expensive, and reflect the changes in transportation with significant delays. Thanks to the ubiquitous cell phone...
Deep learning for driving detection on mobile phones
Просмотров 8198 лет назад
Author: Allen Tran, Metromile Inc. Abstract: Sensor based activity recognition is a critical component of mobile phone based applications aimed at driving detection. Current methodologies consist of hand-engineered features input into discriminative models, and experiments to date have been restricted to small scale studies of O(10) users. Here we show how convolutional neural networks can be u...
Bayesian optimization and its applications for autonomous vehicles
Просмотров 1,6 тыс.8 лет назад
Author: Jeff Schneider, School of Computer Science, Carnegie Mellon University More on www.kdd.org/kdd2016/ KDD2016 Conference is published on videolectures.net/
Online Traffic Speed Forecasting Considering Multiple Periodicities and Complex Patterns
Просмотров 4178 лет назад
Author: Hsing-Kuo Pao, Department of Computer Science and Information Engineering, National Taiwan University Abstract: Intelligent Transportation Systems (ITS) has been developed to aid drivers and other road-users to make a better travel decision. In recent years, many research efforts have been devoted in this field. Being one kind of time-series data, we can analyze the traffic data followi...
Panel on Machine Learning for Large Scale Transportation Systems
Просмотров 5008 лет назад
Panelists: Alexandre Bayen, Department of Electrical Engineering and Computer Sciences, UC Berkeley Chris Pouliot, NextEV Ltd. Jeff Schneider, School of Computer Science, Carnegie Mellon University More on www.kdd.org/kdd2016/ KDD2016 Conference is published on videolectures.net/
Improving Demand Prediction in Bike Sharing System by Learning Global Features
Просмотров 1,6 тыс.8 лет назад
Author: Ming Zeng, Carnegie Mellon University Abstract: A bike sharing system deploys bicycles at many open docking stations and makes them available to the public for shared use. These bikes can be checked-in and checked-out at any of the docking stations. Predicting daily visits is important for service providers to optimize bike allocation and station maintenance. In this paper, we formulate...
Learning Multi-Layer Coarse-to-Fine Representations for Over 10,000 Image Categories
Просмотров 1048 лет назад
Learning Multi-Layer Coarse-to-Fine Representations for Over 10,000 Image Categories
Effective Auto-Encoder for Unsupervised Sparse Representation
Просмотров 5418 лет назад
Effective Auto-Encoder for Unsupervised Sparse Representation
Film2Vec: A Feature-based Film Distributed Representation for Rating Prediction
Просмотров 1988 лет назад
Film2Vec: A Feature-based Film Distributed Representation for Rating Prediction
Applying Deep Learning to Improve Maritime Situational Awareness
Просмотров 4298 лет назад
Applying Deep Learning to Improve Maritime Situational Awareness
Deep Learning for Financial Sentiment Analysis
Просмотров 1,5 тыс.8 лет назад
Deep Learning for Financial Sentiment Analysis
Long-term face tracking in the wild using deep learning
Просмотров 4208 лет назад
Long-term face tracking in the wild using deep learning
Improving Deep Neural Network Design for New Text Data Representations
Просмотров 2278 лет назад
Improving Deep Neural Network Design for New Text Data Representations
Deep Learning for Chemical Compound Stability Prediction
Просмотров 3858 лет назад
Deep Learning for Chemical Compound Stability Prediction
Two Types of Big Data and Three Styles of Deep Learning for AI Applications
Просмотров 2148 лет назад
Two Types of Big Data and Three Styles of Deep Learning for AI Applications
Leveraging Multi-Layer Deep Features for Large-Scale Visual Recognition
Просмотров 3278 лет назад
Leveraging Multi-Layer Deep Features for Large-Scale Visual Recognition
Contextual LSTM (CLSTM) models for Large-scale NLP tasks
Просмотров 1 тыс.8 лет назад
Contextual LSTM (CLSTM) models for Large-scale NLP tasks
Recognizing and Analyzing Ball Screen Defense in the NBA
Просмотров 2648 лет назад
Recognizing and Analyzing Ball Screen Defense in the NBA
Making Strides in Quantifying and Understanding Soccer
Просмотров 4,2 тыс.8 лет назад
Making Strides in Quantifying and Understanding Soccer
Can you please share me the data set
Dr. Crawford is a legend
Hi Ajinkya, Can you please provide link to your paper & opensource code (if any) ?
LMAO AI robot going hard af
This has to be the weirdest presentation video i have ever seen
Oooh I've got my eye on this stuff. Thanks for making it available.
Impressive work! A big leap in the domain of model surrogate!
simply on it ...is Balaji and his network !!!
You can help me with a master’s thesis for my software part (coding) in Python?
The camera man really sucks for focusing on the handsome boy only.
Beautifulll
This is the stupidest thing I've ever skimmed through. Why is it in my professional feed?
Great work, but he speaks so fast ... cant follow
Hi seam Lata
Is me the only one that find it hard to understand his english? he seems to be mumbling too much
Where can I find research paper corresponding to this video?
I despise the way blizzard patches games. It feels so in-human. I wish they had 0 data driven decisions and just played the game and patched it that way! It would feel so much cooler and more fun if they patched it from a human perspective rather than a machine learning algorithm to try to make everyone go down every lane equally. I want something that's fun, not a machine algorithm to make the game as bland and dull as possible. If someone doesn't like something, don't "MAKE" them play it by buffing it into the stratosphere so it overpowers everything. Just make stuff feel cool. I strongly dislike //detest this new age of game design..... I want the way of blizzard to go out the window. It's time for something fresh, better and new......
underrated!!!! I love how the first person asking question referenced the EU Law (2018) and that it will be a hit-piece! Doing a literature research about XAI now, and Ribeiro 2016 is fundamental!
Yes!
K Oi l
The cameraman ruined everything!
wow
Wow
where can I find the same video with only slides but without the voice then?
The paper the speaker wrote contains more details: www.kdd.org/kdd2016/papers/files/adf0755-vanderveldAbr.pdf
Camera man 🤣
This presentation is nicely made. May I ask what tool you used to make this dynamic presentation?
Great piece of work!! Really appreciate! Curious to understand when not to use LIME for tabular and Image data? Secondly, what are pros of LIME over Shaply values when tabular data is concern and GRAD CAM/ SILENCY MAP/ GRADIENT MAP when image data is concern? Thank you in advance!
Who chose the moderator? Barely understandable 24:12... the poor CC is struggling
Think this would apply to social media as a whole.
True
Are the slides posted somewhere? This camera person was horrible
@@atank18 Oh! that'd be amazing, it's been a year but it'll still be useful to be, thanks! I'm sending you a linkedin message so I don't have to share my email here. Thank you!
awesome, precise and simple motivation for LIME
I think the camera should be more focused on the presentation on screen rather than presentator
where i can get this presentation ppt file ?
awesome~
Was the first author giving a presentation of his method, but no damn ppt on the screen
Those slides must be super expensive so the camera just refuses resting on it for more than one second. want to fix on the speaker himself for the most of the time.
Whoever makes this video must be silly. Why does he believe that the speaker is more important than the slides during a presentation? This is just a waste of resources.
What a pity. Good presentation but a stupid record.
where can i find your code ?
wow. Why are you making judgments about the choice of a female voice for the video? I find it amazing that you think the authors chose a female voice to attract viewers. Bet most of the people did not even realize that and came here for the content. This is just a short "commercial" video. If you are interested (I hope that interest didn't come from the "female voice" fact) and need to know more about the algorithm it took me literally two seconds to find the paper dl.acm.org/doi/pdf/10.1145/2939672.2939778.
It would be better if link of slides can be kept in the description section.
Wow, this masterpiece only has 978 views at time of writing! Thanks for the upload #firstcomment
1st comment on 1st comment and 2nd absolute comment here
Is there is any implementation of such work on GitHub using real data ?
source code can be found on Author`s homepage shuozhou.github.io/，synthetic demo included in the package.i`ve experiment on PeMS traffic speed data, it`s comparable to tensor toolbox CP-ALS.
Please could you elaborate on how the coordinate numbers are obtained
Very good presentation. However, I found your code too complicated. Would be great to have a short video and explanation the reason behind this complexity
lol the code is written by C++
Oh what I'd give for those slides.
The paper the speaker wrote contains more details: www.kdd.org/kdd2016/papers/files/adf0755-vanderveldAbr.pdf
very nice explanation!!!
Hard to follow when the presenter is talking about slides and the video doesn't show it. Great until that :(
This is one of the most brilliant applied graph theory lectures i've ever heard.
Sorry, but can you explain the term LOCAL more clearly?
what a pity