Path: csiph.com!news.swapon.de!fu-berlin.de!uni-berlin.de!not-for-mail From: Doug Blank Newsgroups: comp.lang.python.announce Subject: Conx, Easy to use Deep Learning Date: Sat, 19 Aug 2017 08:56:42 -0400 Lines: 29 Approved: python-announce-list@python.org Message-ID: References: Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" X-Trace: news.uni-berlin.de 6MseuE6jqOKhwh5Dx2eqtQqZCIu7BA28+qc7/JqZINcw== Return-Path: X-Original-To: python-announce-list@python.org Delivered-To: python-announce-list@mail.python.org X-Spam-Status: OK 0.042 X-Spam-Evidence: '*H*': 0.92; '*S*': 0.00; 'layers': 0.05; 'url:github': 0.05; 'python': 0.09; 'jupyter': 0.09; 'propagate': 0.09; 'skip:d 60': 0.09; 'api': 0.10; 'format)': 0.16; 'numpy,': 0.16; 'subject:Learning': 0.16; 'url:githubusercontent': 0.16; 'webcam': 0.16; 'wrappers': 0.16; 'creates': 0.18; 'input': 0.18; 'app': 0.18; 'library': 0.20; '(or': 0.22; 'interfaces': 0.23; 'url:io': 0.23; 'message-id:@mail.gmail.com': 0.24; 'discussion': 0.26; "we're": 0.27; '(optional)': 0.29; 'know)': 0.29; 'url:network': 0.29; 'error': 0.29; 'getting': 0.30; 'subject:use': 0.30; 'received:google.com': 0.32; 'deep': 0.32; 'but': 0.34; 'skip:& 20': 0.35; 'integration': 0.35; 'initial': 0.35; 'received:209.85': 0.37; '8bit%:12': 0.38; 'release': 0.38; 'received:io': 0.38; 'received:psf.io': 0.38; 'received:ams1.psf.io': 0.38; 'received:mail1.ams1.psf.io': 0.38; 'received:209': 0.39; 'proto:https': 0.39; 'to:addr:python.org': 0.40; 'standard': 0.40; 'target': 0.60; 'extended': 0.61; 'here:': 0.63; 'students': 0.63; 'easy': 0.64; 'designed': 0.65; 'online': 0.71; 'to:addr:python-announce-list': 0.72; 'researchers': 0.76; 'humans': 0.84; 'subject:Easy': 0.84; 'url:master': 0.84; 'know!': 0.91; 'niche': 0.91; 'robot': 0.91; 'researchers,': 0.97 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=mime-version:from:date:message-id:subject:to; bh=mwoW2Y+DA7lihpGtyaV9P1p/iRxfwYUut+HWp0oBPEI=; b=iuq/bMbLhzXvNJGgVzQP1buquDN9AHKGuld+7rglFfBSsFBUypSB5A/7F0FG+rDE2g 4tABIbg/XOhWFOWg77+sdn2vPgO7sbLQ7KaC6yOz3J7xef+Meg4buUXcBF0Tpl2m1xgG cqCQjBPjc4B+zveF/TfRT1Wb5Fxr1kdAmdemqOdmYjBSIdpU3ThC8NAone081Ne9BtnY MzMIzfzMVm4ltgMSeLIqDCbnByJ3o2pNTBOlyYNh33hIIgSR6lyxoRK7tV4kdiHOWmPE EBeyrQ2zvehU1ZaHKRnIrA3BxIZVuST9T8jooiB2wDldAHLSCtT2r9KeHg6gkDA+7un7 LePw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:from:date:message-id:subject:to; bh=mwoW2Y+DA7lihpGtyaV9P1p/iRxfwYUut+HWp0oBPEI=; b=CAGivYkRUaNZR6BXzciwgQPqGYgND8othUsbxXBeidBxFQwxszlrorD7LqGoRz2YKv oLF4v8wTZZWFjVCWhQU2AtdF+B63p5Tvr6IMrccMQvrmhBGwHVDCy0V/5a1xNPRG3YUD FHPEj6rwPpUziUFV2TbCBVmZbMd/XLACxeD5D7e4LIbRuJyWjuDzEQ4/sjjjKtH9eI2g t2PMwP8pA69MCbZ7avJ6Grl7V6sRV89V71z59jWlAdfCa9IadZojMOy1h1vsddr9GX8v E4Q/bVQd+FURqzWO8kSk1BLeVdRq6UQkax8wZjrtQkfh4TuqNx4zXIOJyXMa+pjkS+SE R/vA== X-Gm-Message-State: AHYfb5hJs/PkqiGBkLq1VrW8bQVYI2Nr/xHiHEV89vFlhVumxhFY+Z86 Js2phaJ8pYlpSbupCnidCaSHDgrwCXe3 X-Received: by 10.200.26.99 with SMTP id q32mr15823680qtk.243.1503147402911; Sat, 19 Aug 2017 05:56:42 -0700 (PDT) X-Mailman-Approved-At: Fri, 25 Aug 2017 08:54:59 -0400 X-Content-Filtered-By: Mailman/MimeDel 2.1.24 X-BeenThere: python-announce-list@python.org X-Mailman-Version: 2.1.24 Precedence: list List-Id: Announcement-only list for the Python programming language List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-Mailman-Original-Message-ID: Xref: csiph.com comp.lang.python.announce:2607 An initial release of new Python library for Deep Learning: conx (pronounced "connects"). Built on Keras, but with enhancements, and designed for researchers, teaching, and learning. Documentation: http://conx.readthedocs.io/ Installation: https://github.com/Calysto/conx What niche does conx fill? * designed for students and researchers that don't want to work with (or don't know) numpy, matplotlib, or Keras functional-api * tight integration with Jupyter notebooks * widget-based app for easy exploration of ANN models * error messages designed for humans * standard input and target dataset API (separate from internal Keras numpy-based format) * supports all Keras layers via thin wrappers * creates standard Keras models * extended propagate functions: propagate_to, propagate_from * designed for use with an online robot simulator (optional) * built-in plotting and webcam interfaces * creates updatable network images (SVG) with activations, like this one: https://raw.githubusercontent.com/Calysto/conx/master/notebooks/network.png We're just getting started, so if you would like to collaborate, or have ideas, please let us know! Discussion group here: https://groups.google.com/forum/#!forum/conx-users