Hopfield

class Hopfield : public BasePlasticity

Public Functions

Hopfield(const int &outputs, const int &batch_size, update_args optimizer = update_args(optimizer_t::sgd), weights_initialization weights_init = weights_initialization(weights_init_t::normal), int epochs_for_convergency = 1, float convergency_atol = 0.01, float delta = .4f, float p = 2.f, int k = 2)

Construct the object using the list of training parameters.

The constructor follows the same nomenclature of the Python counterpart.

Note

Parameters

• outputs – Number of hidden units.

• batch_size – Size of the minibatch.

• optimizer – update_args Optimizer object (default=SGD algorithm).

• weights_init – weights_initialization object (default=uniform initialization in [-1, 1]).

• epochs_for_convergency – Number of stable epochs requested for the convergency.

• convergency_atol – Absolute tolerance requested for the convergency.

• delta – Strength of the anti-hebbian learning

• p – Lebesgue norm of the weights.

• k – Ranking parameter, must be integer that is bigger or equal than 2.

Hopfield(const Hopfield &b)

Copy constructor.

The copy constructor provides a deep copy of the object, i.e. all the arrays are copied and not moved.

Parameters

b – Hopfield object

Hopfield &operator=(const Hopfield &b)

Copy operator.

The operator performs a deep copy of the object and if there are buffers already allocated, the operatore deletes them and then re-allocates an appropriated portion of memory.

Parameters

b – Hopfield object

~Hopfield() = default

Destructor.

Completely delete the object and release the memory of the arrays.