We present the first analysis of the connectome of the vertical lobe (VL) of Octopus vulgaris, a brain structure mediating the acquisition of long-term memory in this behaviorally advanced mollusk. Serial section electron microscopy revealed new types of interneurons, cellular components of extensive modulatory systems, and multiple synaptic motifs. The sensory input to the VL is conveyed via ≈1,800,000 axons that sparsely innervate two parallel and interconnected feedforward networks formed by the two AM types, simple AMs (SAMs) and complex AMS (CAMs). SAMs make up 89.3% of the 25,000,000 AMs, each receiving synaptic input from only a single input neuron on its non-bifurcating primary neurite, suggesting that each input neuron is represented in only ≈12 SAMs. The CAMs, a newly described amacrine type, comprise 1.6% of the amacrine population. Their bifurcating neurites integrate multiple inputs from the input axons and SAMs. While the SAM network appears to feedforward sparse memorizable sensory representations into the VL output layer, the CAMs appear to monitor global activity and feedforward a balancing inhibition for sharpening the stimulus-specific VL output. While sharing morphological and wiring features with circuits supporting associative learning in other animals, the VL has evolved a unique circuit that enables associative learning based strictly on feedforward information flow.