Deep convolutional neural networks comprise a subclass of deep neural networks (DNN) with a constrained architecture that leverages the spatial and temporal structure of the domain they model. Convolutional networks achieve the best predictive performance in areas such as speech and image recognition by hierarchically composing simple local features into complex models. Although DNNs have been use
 
     
       
       
       
      ![東芝、ヒトの「脳」模したチップ開発―人工知能に応用 [インターネットコム]](https://cdn-ak-scissors.b.st-hatena.com/image/square/1be74f3ab8891493fb9e2993bd802d416f0ac65e/height=288;version=1;width=512/https%3A%2F%2Fimage.internetcom.jp%2Fupload%2F20161107%2Fimages%2Fbrain.jpg) 
       
       
       
       
       
      

