Boltzmann MachinesA Boltzmann machine is a probabilistic neural network that defines a probability distribution over binary variables.
Restricted Boltzmann MachinesA restricted Boltzmann machine, or RBM, is a simplified Boltzmann machine with a bipartite structure.
Deep Belief NetworksA deep belief network, or DBN, is a probabilistic generative model formed by stacking multiple layers of latent variables.
Energy-Based ModelsEnergy-based models, or EBMs, define probability distributions using energy functions rather than normalized output probabilities directly.
Flow-Based ModelsFlow-based models are generative models that learn an invertible transformation between a simple probability distribution and a complex data distribution. Unlike many other generative models, flow-based systems provide:
Probabilistic CircuitsProbabilistic circuits are tractable probabilistic models built from simple computational graphs.