diff --git a/dev/.documenter-siteinfo.json b/dev/.documenter-siteinfo.json index ef45ccc..e8a1ad8 100644 --- a/dev/.documenter-siteinfo.json +++ b/dev/.documenter-siteinfo.json @@ -1 +1 @@ -{"documenter":{"julia_version":"1.11.1","generation_timestamp":"2024-11-05T09:10:48","documenter_version":"1.7.0"}} \ No newline at end of file +{"documenter":{"julia_version":"1.11.1","generation_timestamp":"2024-11-05T09:21:36","documenter_version":"1.7.0"}} \ No newline at end of file diff --git a/dev/api/cells/index.html b/dev/api/cells/index.html index 34e4ee7..511973d 100644 --- a/dev/api/cells/index.html +++ b/dev/api/cells/index.html @@ -1,8 +1,8 @@ Cells · RecurrentLayers.jl
GitHub

Cells

RecurrentLayers.RANCell — Type
RANCell((in, out)::Pair;
-kernel_init = glorot_uniform,
-recurrent_kernel_init = glorot_uniform,
-bias = true)

The RANCell, introduced in this paper, is a recurrent cell layer which provides additional memory through the use of gates.

and returns both ht anf ct.

See RAN for a layer that processes entire sequences.

Arguments

  • in => out: Specifies the input and output dimensions of the layer.
  • init: Initialization function for the weight matrices, default is glorot_uniform.
  • bias: Indicates if a bias term is included; the default is true.

Forward

rancell(x, [h, c])

The forward pass takes the following arguments:

  • x: Input to the cell, which can be a vector of size in or a matrix of size in x batch_size.
  • h: The hidden state vector of the cell, sized out, or a matrix of size out x batch_size.
  • c: The candidate state, sized out, or a matrix of size out x batch_size.

If not provided, both h and c default to vectors of zeros.

Examples

rancell = RANCell(3 => 5)
+    kernel_init = glorot_uniform,
+    recurrent_kernel_init = glorot_uniform,
+    bias = true)

The RANCell, introduced in this paper, is a recurrent cell layer which provides additional memory through the use of gates.

and returns both ht anf ct.

See RAN for a layer that processes entire sequences.

Arguments

  • in => out: Specifies the input and output dimensions of the layer.
  • init: Initialization function for the weight matrices, default is glorot_uniform.
  • bias: Indicates if a bias term is included; the default is true.

Forward

rancell(x, [h, c])

The forward pass takes the following arguments:

  • x: Input to the cell, which can be a vector of size in or a matrix of size in x batch_size.
  • h: The hidden state vector of the cell, sized out, or a matrix of size out x batch_size.
  • c: The candidate state, sized out, or a matrix of size out x batch_size.

If not provided, both h and c default to vectors of zeros.

Examples

rancell = RANCell(3 => 5)
 inp = rand(Float32, 3)
 #initializing the hidden states, if we want to provide them
 state = rand(Float32, 5)
@@ -11,34 +11,34 @@
 #result with default initialization of internal states
 result = rancell(inp)
 #result with internal states provided
-result_state = rancell(inp, (state, c_state))
source
RecurrentLayers.IndRNNCell — Type
function IndRNNCell((in, out)::Pair, σ=relu;
-kernel_init = glorot_uniform,
-recurrent_kernel_init = glorot_uniform,
-bias = true)
source
RecurrentLayers.LightRUCell — Type
LightRUCell((in, out)::Pair, σ=tanh;
-kernel_init = glorot_uniform,
-recurrent_kernel_init = glorot_uniform,
-bias = true)
source
RecurrentLayers.MGUCell — Type
MGUCell((in, out)::Pair;
-kernel_init = glorot_uniform,
-recurrent_kernel_init = glorot_uniform,
-bias = true)
source
RecurrentLayers.NASCell — Type
NASCell((in, out)::Pair;
-kernel_init = glorot_uniform,
-recurrent_kernel_init = glorot_uniform,
-bias = true)
source
RecurrentLayers.MUT1Cell — Type
MUT1Cell((in, out)::Pair;
-kernel_init = glorot_uniform,
-recurrent_kernel_init = glorot_uniform,
-bias = true)
source
RecurrentLayers.MUT2Cell — Type
MUT2Cell((in, out)::Pair;
-kernel_init = glorot_uniform,
-recurrent_kernel_init = glorot_uniform,
-bias = true)
source
RecurrentLayers.MUT3Cell — Type
MUT3Cell((in, out)::Pair;
-kernel_init = glorot_uniform,
-recurrent_kernel_init = glorot_uniform,
-bias = true)
source
RecurrentLayers.SCRNCell — Type
function SCRNCell((in, out)::Pair;
-kernel_init = glorot_uniform,
-recurrent_kernel_init = glorot_uniform,
-bias = true,
-alpha = 0.0)
source
+result_state = rancell(inp, (state, c_state))source
RecurrentLayers.IndRNNCell — Type
function IndRNNCell((in, out)::Pair, σ=relu;
+    kernel_init = glorot_uniform,
+    recurrent_kernel_init = glorot_uniform,
+    bias = true)
source
RecurrentLayers.LightRUCell — Type
LightRUCell((in, out)::Pair, σ=tanh;
+    kernel_init = glorot_uniform,
+    recurrent_kernel_init = glorot_uniform,
+    bias = true)
source
RecurrentLayers.LiGRUCell — Type
LiGRUCell((in, out)::Pair;
+    kernel_init = glorot_uniform,
+    recurrent_kernel_init = glorot_uniform,
+    bias = true)
source
RecurrentLayers.MGUCell — Type
MGUCell((in, out)::Pair;
+    kernel_init = glorot_uniform,
+    recurrent_kernel_init = glorot_uniform,
+    bias = true)
source
RecurrentLayers.NASCell — Type
NASCell((in, out)::Pair;
+    kernel_init = glorot_uniform,
+    recurrent_kernel_init = glorot_uniform,
+    bias = true)
source
RecurrentLayers.RHNCell — Type
RHNCell((in, out), depth=3; couple_carry::Bool = true, cell_kwargs...)
source
RecurrentLayers.RHNCellUnit — Type
RHNCellUnit((in, out)::Pair;
+    kernel_init = glorot_uniform,
+    bias = true)
source
RecurrentLayers.MUT1Cell — Type
MUT1Cell((in, out)::Pair;
+    kernel_init = glorot_uniform,
+    recurrent_kernel_init = glorot_uniform,
+    bias = true)
source
RecurrentLayers.MUT2Cell — Type
MUT2Cell((in, out)::Pair;
+    kernel_init = glorot_uniform,
+    recurrent_kernel_init = glorot_uniform,
+    bias = true)
source
RecurrentLayers.MUT3Cell — Type
MUT3Cell((in, out)::Pair;
+    kernel_init = glorot_uniform,
+    recurrent_kernel_init = glorot_uniform,
+    bias = true)
source
RecurrentLayers.SCRNCell — Type
function SCRNCell((in, out)::Pair;
+    kernel_init = glorot_uniform,
+    recurrent_kernel_init = glorot_uniform,
+    bias = true,
+    alpha = 0.0)
source
diff --git a/dev/api/wrappers/index.html b/dev/api/wrappers/index.html index a4f1c0d..c7a39c7 100644 --- a/dev/api/wrappers/index.html +++ b/dev/api/wrappers/index.html @@ -1,2 +1,2 @@ -Cell Wrappers · RecurrentLayers.jl
GitHub

Cell wrappers

+Cell Wrappers · RecurrentLayers.jl
GitHub

Cell wrappers

diff --git a/dev/index.html b/dev/index.html index d7d9141..bf2653d 100644 --- a/dev/index.html +++ b/dev/index.html @@ -1,2 +1,2 @@ -Home · RecurrentLayers.jl
GitHub

RecurrentLayers

RecurrentLayers.jl extends Flux.jl recurrent layers offering by providing implementations of bleeding edge recurrent layers not commonly available in base deep learning libraries. It is designed for a seamless integration with the larger Flux ecosystem, enabling researchers and practitioners to leverage the latest developments in recurrent neural networks.

+Home · RecurrentLayers.jl
GitHub

RecurrentLayers

RecurrentLayers.jl extends Flux.jl recurrent layers offering by providing implementations of bleeding edge recurrent layers not commonly available in base deep learning libraries. It is designed for a seamless integration with the larger Flux ecosystem, enabling researchers and practitioners to leverage the latest developments in recurrent neural networks.

diff --git a/dev/search_index.js b/dev/search_index.js index d24e499..9da457f 100644 --- a/dev/search_index.js +++ b/dev/search_index.js @@ -1,3 +1,3 @@ var documenterSearchIndex = {"docs": -[{"location":"api/cells/#Cells","page":"Cells","title":"Cells","text":"","category":"section"},{"location":"api/cells/","page":"Cells","title":"Cells","text":"RANCell\nIndRNNCell\nLightRUCell\nLiGRUCell\nMGUCell\nNASCell\nRHNCell\nRHNCellUnit\nMUT1Cell\nMUT2Cell\nMUT3Cell\nSCRNCell","category":"page"},{"location":"api/cells/#RecurrentLayers.RANCell","page":"Cells","title":"RecurrentLayers.RANCell","text":"RANCell((in, out)::Pair;\nkernel_init = glorot_uniform,\nrecurrent_kernel_init = glorot_uniform,\nbias = true)\n\nThe RANCell, introduced in this paper, is a recurrent cell layer which provides additional memory through the use of gates.\n\nand returns both ht anf ct.\n\nSee RAN for a layer that processes entire sequences.\n\nArguments\n\nin => out: Specifies the input and output dimensions of the layer.\ninit: Initialization function for the weight matrices, default is glorot_uniform.\nbias: Indicates if a bias term is included; the default is true.\n\nForward\n\nrancell(x, [h, c])\n\nThe forward pass takes the following arguments:\n\nx: Input to the cell, which can be a vector of size in or a matrix of size in x batch_size.\nh: The hidden state vector of the cell, sized out, or a matrix of size out x batch_size.\nc: The candidate state, sized out, or a matrix of size out x batch_size.\n\nIf not provided, both h and c default to vectors of zeros.\n\nExamples\n\nrancell = RANCell(3 => 5)\ninp = rand(Float32, 3)\n#initializing the hidden states, if we want to provide them\nstate = rand(Float32, 5)\nc_state = rand(Float32, 5)\n\n#result with default initialization of internal states\nresult = rancell(inp)\n#result with internal states provided\nresult_state = rancell(inp, (state, c_state))\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.IndRNNCell","page":"Cells","title":"RecurrentLayers.IndRNNCell","text":"function IndRNNCell((in, out)::Pair, σ=relu;\nkernel_init = glorot_uniform,\nrecurrent_kernel_init = glorot_uniform,\nbias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.LightRUCell","page":"Cells","title":"RecurrentLayers.LightRUCell","text":"LightRUCell((in, out)::Pair, σ=tanh;\nkernel_init = glorot_uniform,\nrecurrent_kernel_init = glorot_uniform,\nbias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.LiGRUCell","page":"Cells","title":"RecurrentLayers.LiGRUCell","text":"LiGRUCell((in, out)::Pair;\nkernel_init = glorot_uniform,\nrecurrent_kernel_init = glorot_uniform,\nbias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.MGUCell","page":"Cells","title":"RecurrentLayers.MGUCell","text":"MGUCell((in, out)::Pair;\nkernel_init = glorot_uniform,\nrecurrent_kernel_init = glorot_uniform,\nbias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.NASCell","page":"Cells","title":"RecurrentLayers.NASCell","text":"NASCell((in, out)::Pair;\nkernel_init = glorot_uniform,\nrecurrent_kernel_init = glorot_uniform,\nbias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.RHNCell","page":"Cells","title":"RecurrentLayers.RHNCell","text":"RHNCell((in, out), depth=3; couple_carry::Bool = true, cell_kwargs...)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.RHNCellUnit","page":"Cells","title":"RecurrentLayers.RHNCellUnit","text":"RHNCellUnit((in, out)::Pair;\nkernel_init = glorot_uniform,\nbias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.MUT1Cell","page":"Cells","title":"RecurrentLayers.MUT1Cell","text":"MUT1Cell((in, out)::Pair;\nkernel_init = glorot_uniform,\nrecurrent_kernel_init = glorot_uniform,\nbias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.MUT2Cell","page":"Cells","title":"RecurrentLayers.MUT2Cell","text":"MUT2Cell((in, out)::Pair;\nkernel_init = glorot_uniform,\nrecurrent_kernel_init = glorot_uniform,\nbias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.MUT3Cell","page":"Cells","title":"RecurrentLayers.MUT3Cell","text":"MUT3Cell((in, out)::Pair;\nkernel_init = glorot_uniform,\nrecurrent_kernel_init = glorot_uniform,\nbias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.SCRNCell","page":"Cells","title":"RecurrentLayers.SCRNCell","text":"function SCRNCell((in, out)::Pair;\nkernel_init = glorot_uniform,\nrecurrent_kernel_init = glorot_uniform,\nbias = true,\nalpha = 0.0)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#Cell-wrappers","page":"Cell Wrappers","title":"Cell wrappers","text":"","category":"section"},{"location":"api/wrappers/","page":"Cell Wrappers","title":"Cell Wrappers","text":"RAN\nIndRNN\nLightRU\nLiGRU\nMGU\nNAS\nRHN\nMUT1\nMUT2\nMUT3\nSCRN","category":"page"},{"location":"api/wrappers/#RecurrentLayers.RAN","page":"Cell Wrappers","title":"RecurrentLayers.RAN","text":"RAN(in => out; init = glorot_uniform, bias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.IndRNN","page":"Cell Wrappers","title":"RecurrentLayers.IndRNN","text":"IndRNN((in, out)::Pair, σ = tanh; bias = true, init = glorot_uniform)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.LightRU","page":"Cell Wrappers","title":"RecurrentLayers.LightRU","text":"LightRU((in, out)::Pair; init = glorot_uniform, bias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.LiGRU","page":"Cell Wrappers","title":"RecurrentLayers.LiGRU","text":"LiGRU((in, out)::Pair; init = glorot_uniform, bias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.MGU","page":"Cell Wrappers","title":"RecurrentLayers.MGU","text":"MGU((in, out)::Pair; init = glorot_uniform, bias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.NAS","page":"Cell Wrappers","title":"RecurrentLayers.NAS","text":"NAS((in, out)::Pair; init = glorot_uniform, bias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.RHN","page":"Cell Wrappers","title":"RecurrentLayers.RHN","text":"RHN((in, out)::Pair depth=3; kwargs...)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.MUT1","page":"Cell Wrappers","title":"RecurrentLayers.MUT1","text":"MUT1((in, out)::Pair; kwargs...)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.MUT2","page":"Cell Wrappers","title":"RecurrentLayers.MUT2","text":"MUT1Cell((in, out)::Pair; kwargs...)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.MUT3","page":"Cell Wrappers","title":"RecurrentLayers.MUT3","text":"MUT3((in, out)::Pair; kwargs...)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.SCRN","page":"Cell Wrappers","title":"RecurrentLayers.SCRN","text":"SCRN((in, out)::Pair; kwargs...)\n\n\n\n\n\n","category":"type"},{"location":"","page":"Home","title":"Home","text":"CurrentModule = RecurrentLayers","category":"page"},{"location":"#RecurrentLayers","page":"Home","title":"RecurrentLayers","text":"","category":"section"},{"location":"","page":"Home","title":"Home","text":"RecurrentLayers.jl extends Flux.jl recurrent layers offering by providing implementations of bleeding edge recurrent layers not commonly available in base deep learning libraries. It is designed for a seamless integration with the larger Flux ecosystem, enabling researchers and practitioners to leverage the latest developments in recurrent neural networks.","category":"page"}] +[{"location":"api/cells/#Cells","page":"Cells","title":"Cells","text":"","category":"section"},{"location":"api/cells/","page":"Cells","title":"Cells","text":"RANCell\nIndRNNCell\nLightRUCell\nLiGRUCell\nMGUCell\nNASCell\nRHNCell\nRHNCellUnit\nMUT1Cell\nMUT2Cell\nMUT3Cell\nSCRNCell","category":"page"},{"location":"api/cells/#RecurrentLayers.RANCell","page":"Cells","title":"RecurrentLayers.RANCell","text":"RANCell((in, out)::Pair;\n kernel_init = glorot_uniform,\n recurrent_kernel_init = glorot_uniform,\n bias = true)\n\nThe RANCell, introduced in this paper, is a recurrent cell layer which provides additional memory through the use of gates.\n\nand returns both ht anf ct.\n\nSee RAN for a layer that processes entire sequences.\n\nArguments\n\nin => out: Specifies the input and output dimensions of the layer.\ninit: Initialization function for the weight matrices, default is glorot_uniform.\nbias: Indicates if a bias term is included; the default is true.\n\nForward\n\nrancell(x, [h, c])\n\nThe forward pass takes the following arguments:\n\nx: Input to the cell, which can be a vector of size in or a matrix of size in x batch_size.\nh: The hidden state vector of the cell, sized out, or a matrix of size out x batch_size.\nc: The candidate state, sized out, or a matrix of size out x batch_size.\n\nIf not provided, both h and c default to vectors of zeros.\n\nExamples\n\nrancell = RANCell(3 => 5)\ninp = rand(Float32, 3)\n#initializing the hidden states, if we want to provide them\nstate = rand(Float32, 5)\nc_state = rand(Float32, 5)\n\n#result with default initialization of internal states\nresult = rancell(inp)\n#result with internal states provided\nresult_state = rancell(inp, (state, c_state))\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.IndRNNCell","page":"Cells","title":"RecurrentLayers.IndRNNCell","text":"function IndRNNCell((in, out)::Pair, σ=relu;\n kernel_init = glorot_uniform,\n recurrent_kernel_init = glorot_uniform,\n bias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.LightRUCell","page":"Cells","title":"RecurrentLayers.LightRUCell","text":"LightRUCell((in, out)::Pair, σ=tanh;\n kernel_init = glorot_uniform,\n recurrent_kernel_init = glorot_uniform,\n bias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.LiGRUCell","page":"Cells","title":"RecurrentLayers.LiGRUCell","text":"LiGRUCell((in, out)::Pair;\n kernel_init = glorot_uniform,\n recurrent_kernel_init = glorot_uniform,\n bias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.MGUCell","page":"Cells","title":"RecurrentLayers.MGUCell","text":"MGUCell((in, out)::Pair;\n kernel_init = glorot_uniform,\n recurrent_kernel_init = glorot_uniform,\n bias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.NASCell","page":"Cells","title":"RecurrentLayers.NASCell","text":"NASCell((in, out)::Pair;\n kernel_init = glorot_uniform,\n recurrent_kernel_init = glorot_uniform,\n bias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.RHNCell","page":"Cells","title":"RecurrentLayers.RHNCell","text":"RHNCell((in, out), depth=3; couple_carry::Bool = true, cell_kwargs...)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.RHNCellUnit","page":"Cells","title":"RecurrentLayers.RHNCellUnit","text":"RHNCellUnit((in, out)::Pair;\n kernel_init = glorot_uniform,\n bias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.MUT1Cell","page":"Cells","title":"RecurrentLayers.MUT1Cell","text":"MUT1Cell((in, out)::Pair;\n kernel_init = glorot_uniform,\n recurrent_kernel_init = glorot_uniform,\n bias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.MUT2Cell","page":"Cells","title":"RecurrentLayers.MUT2Cell","text":"MUT2Cell((in, out)::Pair;\n kernel_init = glorot_uniform,\n recurrent_kernel_init = glorot_uniform,\n bias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.MUT3Cell","page":"Cells","title":"RecurrentLayers.MUT3Cell","text":"MUT3Cell((in, out)::Pair;\n kernel_init = glorot_uniform,\n recurrent_kernel_init = glorot_uniform,\n bias = true)\n\n\n\n\n\n","category":"type"},{"location":"api/cells/#RecurrentLayers.SCRNCell","page":"Cells","title":"RecurrentLayers.SCRNCell","text":"function SCRNCell((in, out)::Pair;\n kernel_init = glorot_uniform,\n recurrent_kernel_init = glorot_uniform,\n bias = true,\n alpha = 0.0)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#Cell-wrappers","page":"Cell Wrappers","title":"Cell wrappers","text":"","category":"section"},{"location":"api/wrappers/","page":"Cell Wrappers","title":"Cell Wrappers","text":"RAN\nIndRNN\nLightRU\nLiGRU\nMGU\nNAS\nRHN\nMUT1\nMUT2\nMUT3\nSCRN","category":"page"},{"location":"api/wrappers/#RecurrentLayers.RAN","page":"Cell Wrappers","title":"RecurrentLayers.RAN","text":"RAN(in => out; kwargs...)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.IndRNN","page":"Cell Wrappers","title":"RecurrentLayers.IndRNN","text":"IndRNN((in, out)::Pair, σ = tanh; kwargs...)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.LightRU","page":"Cell Wrappers","title":"RecurrentLayers.LightRU","text":"LightRU((in, out)::Pair; kwargs...)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.LiGRU","page":"Cell Wrappers","title":"RecurrentLayers.LiGRU","text":"LiGRU((in, out)::Pair; kwargs...)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.MGU","page":"Cell Wrappers","title":"RecurrentLayers.MGU","text":"MGU((in, out)::Pair; kwargs...)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.NAS","page":"Cell Wrappers","title":"RecurrentLayers.NAS","text":"NAS((in, out)::Pair; kwargs...)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.RHN","page":"Cell Wrappers","title":"RecurrentLayers.RHN","text":"RHN((in, out)::Pair depth=3; kwargs...)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.MUT1","page":"Cell Wrappers","title":"RecurrentLayers.MUT1","text":"MUT1((in, out)::Pair; kwargs...)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.MUT2","page":"Cell Wrappers","title":"RecurrentLayers.MUT2","text":"MUT1Cell((in, out)::Pair; kwargs...)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.MUT3","page":"Cell Wrappers","title":"RecurrentLayers.MUT3","text":"MUT3((in, out)::Pair; kwargs...)\n\n\n\n\n\n","category":"type"},{"location":"api/wrappers/#RecurrentLayers.SCRN","page":"Cell Wrappers","title":"RecurrentLayers.SCRN","text":"SCRN((in, out)::Pair; kwargs...)\n\n\n\n\n\n","category":"type"},{"location":"","page":"Home","title":"Home","text":"CurrentModule = RecurrentLayers","category":"page"},{"location":"#RecurrentLayers","page":"Home","title":"RecurrentLayers","text":"","category":"section"},{"location":"","page":"Home","title":"Home","text":"RecurrentLayers.jl extends Flux.jl recurrent layers offering by providing implementations of bleeding edge recurrent layers not commonly available in base deep learning libraries. It is designed for a seamless integration with the larger Flux ecosystem, enabling researchers and practitioners to leverage the latest developments in recurrent neural networks.","category":"page"}] }