{"id":857,"date":"2020-12-02T17:26:07","date_gmt":"2020-12-02T16:26:07","guid":{"rendered":"http:\/\/naolink.com\/?page_id=857"},"modified":"2020-12-10T10:52:18","modified_gmt":"2020-12-10T09:52:18","slug":"edge-computing-solutions","status":"publish","type":"page","link":"https:\/\/naolink.com\/index.php\/edge-computing-solutions\/","title":{"rendered":"EDGE COMPUTING SOLUTIONS"},"content":{"rendered":"\n
\"\"<\/figure>\n\n\n\n

Adapted AI Edge Solutions according to the application level.<\/span><\/strong><\/h3>\n\n\n\n

<\/p>\n\n\n\n

From Ultra Low Power to medium and complex Applications<\/strong><\/p>\n\n\n\n

  1. Digital neural network<\/strong> based on the Chain of HW Neuron cells<\/strong> all interconnected<\/li>
  2. AI processors<\/strong> for ML and<\/strong> Edge computing<\/strong><\/li>
  3. AI Embedded Supercaculator<\/strong> for Deep Neural Networks<\/strong>.<\/li><\/ol>\n\n\n\n

    <\/p>\n\n\n\n

    1 – NeuroMem neuromorphic AI chip<\/strong><\/span><\/h3>\n\n\n\n

    The Neuromorphic chip<\/span><\/strong> is a bank of identical neuromorphic memory cells (neurons) which react to digital stimuli and can learn & recognize in real-time.<\/p>\n\n\n\n

    \"\"<\/figure><\/div>\n\n\n\n

    <\/p>\n\n\n\n

    Parallel architecture<\/span><\/strong><\/p>\n\n\n\n

    The NeuroMem unique parallel architecture<\/strong> allows the design of low-power and high-speed AI chips with unlimited neural network capacity:<\/p>\n\n\n\n

    • Neuron cell = memory + processing logic<\/li>
    • Neuron cells are identical and interconnected<\/li>
    • Neurons are accessed simultaneously in broadcast mode<\/li>
    • Neurons work in parallel without the need for a supervisor<\/li><\/ul>\n\n\n\n

      Interchip Cascadability<\/strong><\/span><\/p>\n\n\n\n

      The chip is a chain of 576 neurons<\/strong> and it can be connected with other external chips constituting a daisy-chain, thus increasing the capacity in number of neurons (1152<\/strong>, 1728<\/strong>, and so on …), which depends on the application and variability of data.<\/p>\n\n\n\n

      For 576 neurons x 256 synapses per neuron = 147 456 synaptic connections of 8 bits<\/strong>.<\/span><\/p>\n\n\n\n

      \"\"
      Chain of neurons, daisy-chained and interconnected<\/figcaption><\/figure><\/div>\n\n\n\n
      \"\"
      Stacking of Neural bricks<\/figcaption><\/figure><\/div>\n\n\n\n

      Its Neurons can learn and recognize patterns extracted from any data sources, such as images, audio waveform, bio signals, text and more, with less energy and complexity than modern microprocessors.<\/p>\n\n\n\n

      \"\"<\/figure><\/div>\n\n\n\n

      2 – AI Processor<\/strong><\/span><\/h3>\n\n\n\n

      <\/p>\n\n\n\n

      3 – Embedded Supercalculator<\/strong><\/span><\/h3>\n\n\n\n

      <\/p>\n\n\n\n

      <\/p>\n","protected":false},"excerpt":{"rendered":"

      Adapted AI Edge Solutions according to the application level. From Ultra Low Power to medium and complex Applications Digital neural network based on the Chain of HW Neuron cells all interconnected AI processors for ML and Edge computing AI Embedded Supercaculator for Deep Neural Networks. 1 – NeuroMem neuromorphic AI chip The Neuromorphic chip is<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-857","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/naolink.com\/index.php\/wp-json\/wp\/v2\/pages\/857","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/naolink.com\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/naolink.com\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/naolink.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/naolink.com\/index.php\/wp-json\/wp\/v2\/comments?post=857"}],"version-history":[{"count":26,"href":"https:\/\/naolink.com\/index.php\/wp-json\/wp\/v2\/pages\/857\/revisions"}],"predecessor-version":[{"id":1092,"href":"https:\/\/naolink.com\/index.php\/wp-json\/wp\/v2\/pages\/857\/revisions\/1092"}],"wp:attachment":[{"href":"https:\/\/naolink.com\/index.php\/wp-json\/wp\/v2\/media?parent=857"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}