{
  "id": 235600,
  "title": "What is CONVOLUTIONAL NEURAL NETWORK?",
  "url": "/competitions/plant-pathology-2021-fgvc8/discussion/235600",
  "author_name": "Harsh Jain",
  "post_date": "2021-04-30T10:38:18.221000",
  "votes": 4,
  "comment_count": 0,
  "views": 0,
  "content": "<ol>\n<li><p>CNN's, like neural networks, are made up of neurons with learnable weights and biases. Each neuron receives several inputs, takes a weighted sum over them, passes it through an activation function, and responds with an output. The whole network has a loss function and all the tips and tricks that we developed for neural networks still apply to CNNs.</p></li>\n<li><p>It processes data that has a grid-like arrangement then extracts important features. One huge advantage of using CNNs is that you don't need to do a lot of pre-processing on images.</p></li>\n<li><p>Types of Layers in CNN</p></li>\n<li><p>INPUT LAYER                                                         2. CONVOLUTIONAL LAYER</p></li>\n<li><p>ACTIVATION FUNCTION LAYEr                            4. POOLING LAYER</p></li>\n</ol>\n<p>5 . FULLY-CONNECTED LAYER </p>",
  "messages": [
    {
      "id": 1288784,
      "postDate": "2021-04-30T10:38:18.220Z",
      "content": "<ol>\n<li><p>CNN's, like neural networks, are made up of neurons with learnable weights and biases. Each neuron receives several inputs, takes a weighted sum over them, passes it through an activation function, and responds with an output. The whole network has a loss function and all the tips and tricks that we developed for neural networks still apply to CNNs.</p></li>\n<li><p>It processes data that has a grid-like arrangement then extracts important features. One huge advantage of using CNNs is that you don't need to do a lot of pre-processing on images.</p></li>\n<li><p>Types of Layers in CNN</p></li>\n<li><p>INPUT LAYER                                                         2. CONVOLUTIONAL LAYER</p></li>\n<li><p>ACTIVATION FUNCTION LAYEr                            4. POOLING LAYER</p></li>\n</ol>\n<p>5 . FULLY-CONNECTED LAYER </p>",
      "rawMarkdown": "1.  CNN's, like neural networks, are made up of neurons with learnable weights and biases. Each neuron receives several inputs, takes a weighted sum over them, passes it through an activation function, and responds with an output. The whole network has a loss function and all the tips and tricks that we developed for neural networks still apply to CNNs.\n\n2. It processes data that has a grid-like arrangement then extracts important features. One huge advantage of using CNNs is that you don't need to do a lot of pre-processing on images.\n\n3. Types of Layers in CNN\n\n1. INPUT LAYER                                                         2. CONVOLUTIONAL LAYER\n\n3. ACTIVATION FUNCTION LAYEr                            4. POOLING LAYER\n\n5 . FULLY-CONNECTED LAYER ",
      "votes": 4
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "1288784": "1.  CNN's, like neural networks, are made up of neurons with learnable weights and biases. Each neuron receives several inputs, takes a weighted sum over them, passes it through an activation function, and responds with an output. The whole network has a loss function and all the tips and tricks that we developed for neural networks still apply to CNNs.\n\n2. It processes data that has a grid-like arrangement then extracts important features. One huge advantage of using CNNs is that you don't need to do a lot of pre-processing on images.\n\n3. Types of Layers in CNN\n\n1. INPUT LAYER                                                         2. CONVOLUTIONAL LAYER\n\n3. ACTIVATION FUNCTION LAYEr                            4. POOLING LAYER\n\n5 . FULLY-CONNECTED LAYER "
  }
}