| 开发人员: | differential enterprises (11) | ||
| 价格: | 免费 | ||
| 排名: | 0 | ||
| 评价: | 0 我要评价 | ||
| 列表: | 1 + 0 | ||
| 积分: | 7 + 0 ¡ | ||
| 积分 +1 | |||
说明
Now supporting binary classification problems.
See What's New In This Version to learn about all the latest updates!
This is a "no code" baseline app to serve as a test bed for basis function approximation methods, which are fairly simple (comparatively speaking) machine learning methods involving a single fully connected inner layer, and are usable for solving general smooth-ish function fits. There is no need to install a myriad of Python packages or other tools to use this. Simply download the app from the app store and read in your CSV file.
The legendary automotive miles per gallon data set which pre-dates Tensorflow and many of its users originating from one of the infamous "malaise eras" is uploaded here in the proper CSV format for this system as a tutorial data set for learning the system:
https://diffent.com/mpgfull.csv
Original data source & background:
https://www.tensorflow.org/tutorials/keras/regression
More detailed use instructions at https://diffent.com/simpleml.pdf
Features:
two basis function types (gauss & multi-quadric)
two distance metrics (Euclidean and Manhattan)
adjustable shape parameter
flexible on-screen data column selector
constant or variable basis function widths
some improper data flagging (question marks or non-numeric characters in data; however, scientific notation is supported e.g. 4.2e1
optional input variable normalization
model complexity hyperparameter adjustments (manual)
auto withhold of points for train/test split (user controllable amount via fraction of original points)
actual versus predicted plots for train, test, and out of sample evaluation points
actual versus predicted data exported to annotated columnar text files
plots in portable HTML for easy use in other systems
hyperparameters stored as user defaults
Variable importance is estimated by leaving a variable out of an already solved model
and comparing RMS error of training data set to full variable RMS error. If RMS doesn't change much,
the variable was not very important. Results reported out as (RMSchange/RMS - 1) per variable in
lower green output window.
User can apply this information to remove variables from models that are less important,
for improved out of sample performance.
屏幕截图
新版变化
- 版本: 5.9
- 已更新:
- Auto weight unbalanced binary output values in residual / sum of square error computation (for classification problems) based on the actual data imbalance ratio. For example, if you have 25 outputs at 1 and 75 outputs at 0 in a 100 point data set, the imbalance ratio is 3 to 1, so we weight the errors on the actual 1 values to be more important by a factor 3, so that the solver will focus on those better. This factor may be high, but we leave it there for now.
Allow the "max down count" that can occur before stopping is triggered during a fwd stepwise solve to be 10 (was 2).
Output the so-called precision of a binary outcome solve for the 1 target value during a stepwise solve. The following right hand side variables are integer counts.
float mlPrecision = (float)correctBinary1/((float)(correctBinary1 + (actualBinary0 - correctBinary0)));
Is this the only definition possible for "precision?" Doubtful. This is why we output the raw ratios (confusion matrix) for further analysis.
价格
- 今天: 免费
- 最小值: 免费
- 最大值: $5.99
可选
开发人员
- differential enterprises
- 平台: iOS 应用 (6) macOS 应用 (3) Windows 应用 (2)
- 列表: 5 + 2
- 积分: 63 + 18 ¡
- 排名: 0
- 评价: 0
- 折扣: 0
- 视频: 0
- RSS: 订阅
积分
-
- 734 Sero'
-
- 1,307 Anthony
-
- 876 眰恦（眰恦）
-
- 566 dl
-
- 627 Raphael Pinheiro
-
- 9,283 Simon Chan
排名
未找到 ☹️
列表
- (2,962) Mac Owned
- 9,283 Simon Chan
- 307
评价
抢先评价一下吧 🌟
其他信息
https://medium.com/@nttp/yet-another-boston-housing-data-example-103b4096f154您可能还喜欢
-
- DuckDuckGo Browser, Search, AI
- macOS 应用: 工具 来自: DuckDuckGo, Inc.
- * 免费
- 列表: 11 + 3 排名: 0 评价: 0
- 积分: 11 + 2,128,033 (4.9) 版本: 7.169.0 At DuckDuckGo, we believe the best way to protect your personal information from hackers, scammers, and privacy-invasive companies is to stop it from being collected at all. That's why ⥯
-
- NordVPN: VPN Fast & Secure
- macOS 应用: 工具 来自: Nordvpn S.A.
- * 免费
- 列表: 0 + 4 排名: 0 评价: 0
- 积分: 4 + 585,900 (4.7) 版本: 8.45.0 Looking for a way to be more private online? Here it is! With NordVPN, one tap is all you need to mask your IP address, encrypt your traffic, and enjoy the internet the way it was ... ⥯
-
- Color Widgets
- macOS 应用: 工具 来自: MM Apps, Inc.
- * 免费
- 列表: 0 + 2 排名: 0 评价: 0
- 积分: 5 + 468,728 (4.6) 版本: 6.3.2 Color Widgets makes adding aesthetic and handy widgets to your Home Screen and Lock Screen easy. Browse thousands of predesigned widgets or, better yet, design your own with the ... ⥯
-
- Free VPN by Free VPN .org™
- macOS 应用: 工具 来自: Free VPN LLC
- * 免费
- 列表: 0 + 1 排名: 0 评价: 0
- 积分: 2 + 429,313 (4.5) 版本: 4.034 Free VPN, #1 - VPN for secure browsing on iPhone, iPad & Mac. Tired of slow connections, privacy risks or can't access your favorite shows and videos. Free VPN by Free VPN.org™ gives ... ⥯
-
- VPNIFY - Unlimited VPN
- macOS 应用: 工具 来自: Neonetworks solution ltd
- * 免费
- 列表: 0 + 0 排名: 0 评价: 0
- 积分: 2 + 89,494 (4.5) 版本: 2.3.35 vpnify is the best VPN & UNLIMITED 100% FREE high speed VPN Proxy on for your iOS device. It is highly secure with military-grade encryption so you can safely navigate public, business ⥯
-
- V2Box - V2ray Client
- macOS 应用: 工具 来自: techlaim
- 免费
- 列表: 3 + 1 排名: 0 评价: 0
- 积分: 10 + 75,911 (4.7) 版本: 9.5 V2box - VPN Internet network proxy , Supports multiple proxy protocols, such as Shadowsocks, V2ray, Vmess, Trojan , SSH , Socks Features: - Support for adding custom servers proxy ... ⥯
-
- AdBlock Pro for Safari
- macOS 应用: 工具 来自: Crypto Inc.
- * 免费
- 列表: 3 + 3 排名: 0 评价: 0
- 积分: 29 + 60,273 (4.5) 版本: 11.3.0 Since 2015, AdBlock Pro for Safari has been trusted by millions of users and featured by Apple multiple times. Enhance your browsing experience on iPhone, iPad, Mac, and Vision Pro ... ⥯
-
- VPN - Fast VPN Potato
- macOS 应用: 工具 来自: FASTPOTATO PTE. LTD.
- * 免费
- 列表: 0 + 0 排名: 0 评价: 0
- 积分: 1 + 59,178 (4.7) 版本: 21.6 PotatoVPN protects your online privacy as an unlimited VPN proxy, offering a super service for those seeking a free VPN for your iPhone. Enjoy ultra-fast speeds, unlimited bandwidth, ... ⥯
-
- Flip Clock - digital widgets
- macOS 应用: 工具 来自: 翠玲 施
- * 免费
- 列表: 0 + 0 排名: 0 评价: 0
- 积分: 4 + 56,164 (4.6) 版本: 6.8 Flip Clock is a classic desktop digital clock. The desktop clock widget supports displaying seconds and a calendar. Clock can be displayed on lock screen and standby screen. - Show ... ⥯
-
- Deliveries: a package tracker
- macOS 应用: 工具 来自: Junecloud LLC
- * 免费
- 列表: 3 + 9 排名: 0 评价: 0
- 积分: 9 + 34,276 (4.7) 版本: 9.6 Deliveries helps you keep track of all your packages, so you always know when they re going to arrive. Whether it's the latest gadget you've preordered online, or a new graphic novel ... ⥯
-
- Speedify: Fast Bonding VPN
- macOS 应用: 工具 来自: Connectify, Inc.
- * 免费
- 列表: 0 + 0 排名: 0 评价: 0
- 积分: 1 + 29,709 (4.7) 版本: 15.6.1 Boost your internet speed with Speedify, the only VPN that keeps you always online by joining multiple internet sources (4G LTE, 5G, Wi-Fi, Starlink, Satellite) into one bonded ... ⥯
-
- World Clock : Time Calculator
- macOS 应用: 工具 来自: Lasmit TLB Ltd
- * 免费
- 列表: 1 + 0 排名: 0 评价: 0
- 积分: 0 + 27,183 (4.7) 版本: 2025.7 Over 1,000,000 downloads and over 44,000 ratings worldwide. **Featured in "Utilities > Apps We Love" in the App Store (US)** **Featured in "Cool Clocks and Timers" of the App Store ... ⥯
-
- Mena VPN: super fast browsing
- macOS 应用: 工具 来自: MenaVPN Holding BV
- * 免费
- 列表: 0 + 0 排名: 0 评价: 0
- 积分: 2 + 26,896 (4.6) 版本: 3.0.11 Secure Your Online Presence with MenaVPN Welcome to MenaVPN, the ultimate shield for your digital life. Mena VPN service is committed to fortifying your online privacy, ensuring that ... ⥯
-
- Authenticator App - OneAuth
- macOS 应用: 工具 来自: Zoho Corporation
- 免费
- 列表: 0 + 0 排名: 0 评价: 0
- 积分: 1 + 24,131 (4.7) 版本: 4.0.3 OneAuth is an industry standard authenticator app developed by Zoho. You can now enable TFA and secure all your online accounts like Twitter, Facebook, LinkedIn, and more. Over 1 ... ⥯