Learning permits animals to attach meaning and context to sensory stimuli. We are interested in how memories are coded in neural networks in the brain, and appropriately retrieved and utilized to guide behavior. In the fruit fly olfactory memories of particular value are represented within sparse populations of odor-activated Kenyon cells (KCs) in the mushroom body ensemble. Current models suggest that during learning reinforcing dopaminergic neurons skew the mushroom body network by driving zonally-restricted plasticity at synaptic junctions between the KCs and subsets of the overall small collection of mushroom body output neurons. Reactivation of the skewed KC-output neuron network retrieves memory of odor valence and guides appropriate approach or avoidance behavior. Our recent work suggests that skews in the KC-output neuron network might also account for state-dependent memory retrieval and memory re-evaluation.