ANNarchy 4.8.2
  • ANNarchy
  • Installation
  • Tutorial
  • Manual
  • Notebooks
  • Reference

  • Reference
  • Core components
    • Population
    • Projection
    • Neuron
    • Synapse
    • Monitor
    • PopulationView
    • Dendrite
    • Network
  • Configuration
    • setup
    • compile
    • clear
    • reset
    • set_seed
    • get_population
    • get_projection
    • populations
    • projections
    • monitors
  • Simulation
    • simulate
    • simulate_until
    • step
    • parallel_run
    • enable_learning
    • disable_learning
    • get_time
    • set_time
    • get_current_step
    • set_current_step
    • dt
  • Neuron models
    • LeakyIntegrator
    • Izhikevich
    • IF_curr_exp
    • IF_cond_exp
    • IF_curr_alpha
    • IF_cond_alpha
    • HH_cond_exp
    • EIF_cond_alpha_isfa_ista
    • EIF_cond_exp_isfa_ista
  • Synapse models
    • STP
    • STDP
    • Hebb
    • Oja
    • IBCM
  • Inputs
    • InputArray
    • TimedArray
    • PoissonPopulation
    • TimedPoissonPopulation
    • SpikeSourceArray
    • HomogeneousCorrelatedSpikeTrains
    • CurrentInjection
    • DecodingProjection
    • ImagePopulation
    • VideoPopulation
  • IO
    • save
    • load
    • save_parameters
    • load_parameters
  • Utilities
    • report
  • Random Distributions
    • Uniform
    • DiscreteUniform
    • Normal
    • LogNormal
    • Exponential
    • Gamma
    • Binomial
  • Functions and Constants
    • add_function
    • functions
    • Constant
    • get_constant
  • Plotting
    • raster_plot
    • histogram
    • inter_spike_interval
    • coefficient_of_variation
    • population_rate
    • smoothed_rate
  • Callbacks
    • every
    • callbacks_enabled
    • disable_callbacks
    • enable_callbacks
    • clear_all_callbacks
  • Convolution
    • Convolution
    • Pooling
    • Transpose
    • Copy
  • BOLD monitoring
    • BoldMonitor
    • BoldModel
    • balloon_RN
    • balloon_RL
    • balloon_CN
    • balloon_CL
    • balloon_maith2021
    • balloon_two_inputs
  • Tensorboard logging
    • Logger
  • ANN-to-SNN conversion
    • ANNtoSNNConverter

On this page

  • Pooling
    • Parameters
    • Methods
      • connect_pooling
      • connectivity_matrix
      • load
      • receptive_fields
      • save
      • save_connectivity

Pooling

extensions.convolution.Pooling.Pooling(
    self,
    pre,
    post,
    target,
    psp='pre.r',
    operation='max',
    name=None,
    copied=False,
)

Performs a pooling operation (e.g. max.pooling) on the pre-synaptic population.

Each post-synaptic neuron covers a specific region (extent) of the pre-synaptic population, over which the result of the operation on firing rates will be assigned to sum(target).

The extent is automatically computed using the geometry of the populations, but can be specified in the `connect_pooling()`` methods.

Example:

inp = ann.Population(geometry=(100, 100), neuron=ann.Neuron(parameters="r = 0.0"))
pop = ann.Population(geometry=(50, 50), neuron=ann.Neuron(equations="r = sum(exc)"))

proj = Pooling(inp, pop, 'exc', operation='max') # max-pooling
proj.connect_pooling() # extent=(2, 2) is implicit

Parameters

Name Type Description Default
pre pre-synaptic population (either its name or a Population object). required
post post-synaptic population (either its name or a Population object). required
target type of the connection required
operation pooling function to be applied (“max”, “min”, “mean”) 'max'

Methods

Name Description
connect_pooling
connectivity_matrix Not available.
load Not available.
receptive_fields Not available.
save Not available.
save_connectivity Not available.

connect_pooling

extensions.convolution.Pooling.Pooling.connect_pooling(extent=None, delays=0.0)

Parameters

Name Type Description Default
extent tuple extent of the pooling area expressed in the geometry of the pre-synaptic population (e.g (2, 2)). In each dimension, the product of this extent with the number of neurons in the post-synaptic population must be equal to the number of pre-synaptic neurons. Default: None. None
delays float synaptic delay in ms 0.0

connectivity_matrix

extensions.convolution.Pooling.Pooling.connectivity_matrix(fill=0.0)

Not available.

load

extensions.convolution.Pooling.Pooling.load(filename)

Not available.

receptive_fields

extensions.convolution.Pooling.Pooling.receptive_fields(
    variable='w',
    in_post_geometry=True,
)

Not available.

save

extensions.convolution.Pooling.Pooling.save(filename)

Not available.

save_connectivity

extensions.convolution.Pooling.Pooling.save_connectivity(filename)

Not available.

Convolution
Transpose
 

Copyright Julien Vitay, Helge Ülo Dinkelbach, Fred Hamker