Feed: What's New. Object2Vec is a new supervised learning algorithm used in applications where there are similar words, phrases, and sentences for the model to train and perform inference upon. Specific examples include building document classification systems where documents are mapped to labels, movie recommendation systems where user ratings are mapped to movies, and information retrieval systems to determine text similar to phrases that the user is searching for. IP Insights is a new unsupervised learning algorithm that identifies suspicious online behavior by analyzing the IP address of a request. The algorithm uses statistical modeling and neural networks to associate ... Read More

Feed: What's New. With this capability, you can view the AWS resource inventory from multiple accounts and Regions in the AWS Config console through a central account. You can also use AWS Config aggregator APIs to retrieve data for display in your internal dashboards. The data aggregation capability is also integrated with AWS Organizations, so you can centrally retrieve this data for any account within your organization.  You can get started by enabling AWS Config and AWS Config rules in your accounts. Next, create an aggregator and provide a list of AWS account IDs. For AWS Organizations customers, provide the ... Read More

Feed: What's New. Each registered event source can process records with a throughput of up to 2MB per second per shard. By registering your event sources as Kinesis data stream consumers, you can run multiple high performance, low-latency serverless stream processing applications on a single Kinesis data stream. Please visit our product page for more information about AWS Lambda or log in to the AWS Lambda console to get started ... Read More

Feed: SAS Blogs. Author: Mike Pflug. Data management gets lost in the enthusiasm around Artificial intelligence (AI) and machine learning (ML). Not surprising, when it's an algorithm that decides what search results to show you, guides the self-driving cars on the roads, and powers the anti-fraud bots that monitor every credit card transaction we make. Charles Christian of the Indiana Health Information Exchange speaks for many of us when he asks: “Why can’t we do that in healthcare?” Health and Human Services (HHS) agencies across the country have been slow to adopt these advanced analytics. Why is this? Is our ... Read More

Feed: SAS Blogs. Author: Makoto Unemi (畝見 真). PythonからSAS Viyaの機能を利用するための基本パッケージであるSWATと、よりハイレベルなPython向けAPIパッケージであるDLPyを使用して、Jupyter NotebookからPythonでSAS Viyaの機能を使用して一般物体検出（Object Detection）を試してみました。  今回は、弊社で用意した数枚の画像データを使用して、処理の流れを確認するだけなので、精度に関しては度返しです。  大まかな処理の流れは以下の通りです。 １．必要なパッケージ（ライブラリ）のインポートとセッションの作成２．一般物体検出向け学習用データの作成３．モデル構造の定義４．モデル生成（学習）５．物体検出（スコアリング）  １．必要なパッケージ（ライブラリ）のインポートとセッションの作成 swatやdlpyなど、必要なパッケージをインポートします。 from swat import * import sys sys.path.append(dlpy_path) from dlpy.model import * from dlpy.layers import * from dlpy.applications import * from dlpy.utils import * from dlpy.images import ImageTable   from dlpy.splitting import two_way_split from dlpy.blocks import * import cv2 import numpy as np import pandas as pd import random import matplotlib.pyplot as plt from PIL import Image   from IPython.display import display 次にSAS ViyaのインメモリーエンジンであるCAS（Cloud Analytic Services）に接続しセッションを作成し、必要なアクションセットをロードし、ライブラリを作成します。 s = CAS(host, port, user, password) s.loadactionset('image') s.loadactionset('deepLearn') s.table.addcaslib(activeonadd=False,datasource={'srctype':'path'}, name='dnfs',path=path,subdirectories=True) ２．一般物体検出向け学習用データの作成DLPyに搭載されているcreate_object_detection_table()メソッドを使用することで、一般物体検出向けに、必要なフォーマットの学習用データを簡単に作成することができます。create_object_detection_table()メソッドに関しては、こちらのブログも参照ください。 object_detection_targets = create_object_detection_table(s, data_path = '/opt/sasinside/DemoData/DeepLearning/object_detection_dlpy/trainData/', ... Read More

Feed: R-bloggers. Author: Dr. Shirin Glander. On November 7th, Uwe Friedrichsen and I gave our talk from the JAX conference 2018: Deep Learning – a Primer again at the W-JAX in Munich. A few weeks before, I gave a similar talk at two events about Demystifying Big Data and Deep Learning (and how to get started). Here are the two very similar presentations from these talks: Related To leave a comment for the author, please follow the link and comment on their blog: Shirin's playgRound. R-bloggers.com offers daily e-mail updates about R news and tutorials on topics such as: Data ... Read More

Feed: R-bloggers. Author: Keith Goldfeld. I’ve been inspired by two recent talks describing the challenges of using instrumental variable (IV) methods. IV methods are used to estimate the causal effects of an exposure or intervention when there is unmeasured confounding. This estimated causal effect is very specific: the complier average causal effect (CACE). But, the CACE is just one of several possible causal estimands that we might be interested in. For example, there’s the average causal effect (ACE) that represents a population average (not just based the subset of compliers). Or there’s the average causal effect for the exposed or ... Read More

Feed: Planet big data. Author: Ted Schadler. We recently evaluated 12 midsize digital experience agencies in “The Forrester Wave™: Midsize Digital Experience Agencies, Q4 2018.” While nobody likes the word “midsize,” we all should pause and consider why a smaller agency can often be the best fit. In the 36 customer reference calls, we heard over and over again that these smaller specialists — 500 to 2,700 dedicated digital experience staff members — were a great cultural fit, big enough to do complex projects, more agile than the “big guys,” and “an extension to my team.” In this world of co-innovation, this ... Read More

Feed: Blog. Author: hendryjullius; Database professionals must handle many different tasks during the work day, ranging from creating queries and scripts to comparing and editing dataset results, just to name a few. Whether you’re a DBA or a developer, you may have some frequently repeated responsibilities and goals, which means there is an opportunity to simplify and automate tasks to be more productive on a daily basis.A good database tool can help you to do just that. Greg Robidoux’s whitepaper, Key Considerations for Selecting a Database Tool, discusses some of the tasks that database professionals deal with on a regular ... Read More

Feed: What's New. AWS Auto Scaling automates capacity management for various AWS services, including Amazon EC2, by tracking capacity utilization. Now, you can use Predictive Scaling in AWS Auto Scaling to scale your Amazon EC2 capacity in advance of traffic changes. Auto Scaling enhanced with Predictive Scaling delivers faster, simpler, and more accurate capacity provisioning, resulting in lower cost and more responsive applications. Predictive Scaling predicts future traffic based on daily and weekly trends, including regularly-occurring spikes, and provisions the right number of EC2 instances in advance of anticipated changes. Provisioning the capacity just in time for an impending load ... Read More