link to a video that further explains the receptive field
Source Link
nbro
  • 31.2k
  • 8
  • 65
  • 130

The circles in the visible stack of the cyan block represent the neurons (or, more precisely, their activations or outputs). We only see $k=5$ neurons stacked: this corresponds to the application of $k=5$ different kernels (i.e. weights) to that specific subset of the input (aka receptive fieldreceptive field), hence the sparse connectivity of CNNs. So, these neurons, in the same stack, are looking at the same small subset of the input, but with different weights (i.e. kernels). The neurons, which are not shown in this diagram, that are on the same (vertical) 2d plane (known as feature map) of the same neuron (e.g. the first that we see from left to right) in the cyan volume are the neurons that share the same weights, i.e. we use the same kernel to produce their outputs.

The circles in the visible stack of the cyan block represent the neurons (or, more precisely, their activations or outputs). We only see $k=5$ neurons stacked: this corresponds to the application of $k=5$ different kernels (i.e. weights) to that specific subset of the input (aka receptive field), hence the sparse connectivity of CNNs. So, these neurons, in the same stack, are looking at the same small subset of the input, but with different weights (i.e. kernels). The neurons, which are not shown in this diagram, that are on the same (vertical) 2d plane (known as feature map) of the same neuron (e.g. the first that we see from left to right) in the cyan volume are the neurons that share the same weights, i.e. we use the same kernel to produce their outputs.

The circles in the visible stack of the cyan block represent the neurons (or, more precisely, their activations or outputs). We only see $k=5$ neurons stacked: this corresponds to the application of $k=5$ different kernels (i.e. weights) to that specific subset of the input (aka receptive field), hence the sparse connectivity of CNNs. So, these neurons, in the same stack, are looking at the same small subset of the input, but with different weights (i.e. kernels). The neurons, which are not shown in this diagram, that are on the same (vertical) 2d plane (known as feature map) of the same neuron (e.g. the first that we see from left to right) in the cyan volume are the neurons that share the same weights, i.e. we use the same kernel to produce their outputs.

added 143 characters in body
Source Link
nbro
  • 31.2k
  • 8
  • 65
  • 130

Essentially, yesThe filters in a CNN correspond to the weights of an MLP. 

A neuron in a CNN can be viewed as performing exactly the same operation as a neuron in an MLP. The big differences between a CNN and an MLP (as explained also in the other answer) are

Essentially, yes. A neuron in a CNN can be viewed as performing exactly the same operation as a neuron in an MLP. The big differences between a CNN and an MLP (as explained also in the other answer) are

The filters in a CNN correspond to the weights of an MLP. 

A neuron in a CNN can be viewed as performing exactly the same operation as a neuron in an MLP. The big differences between a CNN and an MLP (as explained also in the other answer) are

added 143 characters in body
Source Link
nbro
  • 31.2k
  • 8
  • 65
  • 130
  • Weight sharing: Some neurons (not all!) in the same convolutional layer share the same weights. The convolution (or cross-correlation) is the operation that implements this partial forward pass with the same weights for different neurons.

  • Neurons in a CNN only look at a subset of the input and not all inputs (i.e. receptive field), which leads to some notion of sparse connectivity

  • A convolutional layer, in a CNN, is composed of neurons in a 3d dimensional volume (or, more precisely, their activations are organized in a 3d volume), rather than a 1-dimensional one, as in an MLP.

  • CNNs may use subsampling (aka pooling)

  • Weight sharing: Some neurons (not all!) in the same convolutional layer share the same weights.

  • Neurons in a CNN only look at a subset of the input and not all inputs (i.e. receptive field), which leads to some notion of sparse connectivity

  • A convolutional layer, in a CNN, is composed of neurons in a 3d dimensional volume (or, more precisely, their activations are organized in a 3d volume), rather than a 1-dimensional one, as in an MLP.

  • CNNs may use subsampling (aka pooling)

  • Weight sharing: Some neurons (not all!) in the same convolutional layer share the same weights. The convolution (or cross-correlation) is the operation that implements this partial forward pass with the same weights for different neurons.

  • Neurons in a CNN only look at a subset of the input and not all inputs (i.e. receptive field), which leads to some notion of sparse connectivity

  • A convolutional layer, in a CNN, is composed of neurons in a 3d dimensional volume (or, more precisely, their activations are organized in a 3d volume), rather than a 1-dimensional one, as in an MLP.

  • CNNs may use subsampling (aka pooling)

added 721 characters in body
Source Link
nbro
  • 31.2k
  • 8
  • 65
  • 130
Loading
added 16 characters in body
Source Link
nbro
  • 31.2k
  • 8
  • 65
  • 130
Loading
added 69 characters in body
Source Link
nbro
  • 31.2k
  • 8
  • 65
  • 130
Loading
added 69 characters in body
Source Link
nbro
  • 31.2k
  • 8
  • 65
  • 130
Loading
Source Link
nbro
  • 31.2k
  • 8
  • 65
  • 130
Loading