ANNarchy 5.0.0
  • ANNarchy
  • Installation
  • Tutorial
  • Manual
  • Notebooks
  • Reference

  • ANNarchy
  • Core components
    • Network
    • Population
    • Projection
    • Monitor
    • PopulationView
    • Dendrite
  • Neuron and Synapse models
    • Neuron
    • Synapse
    • Parameter
    • Variable
    • Creating
    • Pruning
    • Constant
  • 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
    • Hebb
    • Oja
    • IBCM
    • STP
    • STDP
  • Inputs
    • InputArray
    • TimedArray
    • PoissonPopulation
    • TimedPoissonPopulation
    • SpikeSourceArray
    • HomogeneousCorrelatedSpikeTrains
    • CurrentInjection
    • DecodingProjection
    • ImagePopulation
    • VideoPopulation
  • Random Distributions
    • Uniform
    • DiscreteUniform
    • Normal
    • LogNormal
    • Exponential
    • Gamma
    • Binomial
  • Functions
    • add_function
    • functions
  • Callbacks
    • every
  • Utilities
    • report
    • timeit
    • sparse_random_matrix
    • sparse_delays_from_weights
    • magic_network
  • 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
  • DEPRECATED Top-level API
    • setup
    • compile
    • clear
    • reset
    • set_seed
    • get_population
    • get_projection
    • populations
    • projections
    • monitors
    • simulate
    • simulate_until
    • step
    • enable_learning
    • disable_learning
    • get_time
    • set_time
    • get_current_step
    • set_current_step
    • dt
    • save
    • load
    • save_parameters
    • load_parameters
    • callbacks_enabled
    • disable_callbacks
    • enable_callbacks
    • clear_all_callbacks

On this page

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

Pooling

Pooling(
    self,
    pre,
    post,
    target,
    psp='pre.r',
    operation='max',
    name=None,
    copied=False,
    net_id=0,
)

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 `pooling()`` methods.

Example:

import ANNarchy as ann
from ANNarchy.extensions.convolution import Pooling

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

proj = net.connect(Pooling(inp, pop, 'exc', operation='max')) # max-pooling
proj.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
pooling Connects the Pooling projection.
save_connectivity Not available.
save Not available.
load Not available.
receptive_fields Not available.
connectivity_matrix Not available.

pooling

pooling(extent=None, delays=0.0)

Connects the Pooling projection.

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

save_connectivity

save_connectivity(filename)

Not available.

save

save(filename)

Not available.

load

load(filename)

Not available.

receptive_fields

receptive_fields(variable='w', in_post_geometry=True)

Not available.

connectivity_matrix

connectivity_matrix(fill=0.0)

Not available.

Convolution
Transpose
 

Copyright Julien Vitay, Helge Ülo Dinkelbach, Fred Hamker