A Drosophila Whole-Connectome Network Can Learn Human-Designed Cognitive Tasks

Joonghui Cho; Minchan Kang; Daeshik Kim

cs.LGOct 7, 2026

A Drosophila Whole-Connectome Network Can Learn Human-Designed Cognitive Tasks

Authors: Joonghui Cho, Minchan Kang, Daeshik Kim

Organizations: Korea Advanced Institute of Science and Technology (KAIST)

Abstract

Can a biological wiring diagram serve as a useful computational substrate beyond the behaviors for which it evolved? We use the publicly released MaleCNS v1.0 connectome, reconstructed from a single adult male Drosophila specimen, as the fixed recurrent topology of an artificial network. We train separate models for bounded addition and for a controlled grounded relational language task built from a fixed 100-word lexicon. In both models, one scalar is learned per anatomical edge. The anatomical graph reaches 92.77% mean accuracy on held-out addition, compared with 67.93% for directed degree-preserving rewires. On the strict paired language endpoint, which matches original and order-reversed scenes to their corresponding descriptions, it reaches 61.59% across four fixed interfaces, compared with 44.17% for matched rewires. At the canonical interface, it ranks first in a fixed 21-graph comparison. On the matched 48-group intervention subset, shuffling task-defined sensory features reduces its score from 60.94% to 19.27%. Together, these results show that higher-order MaleCNS wiring provides a reusable inductive bias for bounded addition and grounded relational language.

Figures & tables

Figure 1: Study design. (a) The processed MaleCNS v1.0 adjacency fixes the recurrent support, and each retained directed edge carries one learned scalar. The anatomical rendering shows a deterministic sample of 3,000 neuron skeletons. The overlaid nodes and arrows are schematic. Directed-degree-preserving rewires retain each node’s in- and out-degree. (b) Addition and grounded relational language are separate fits on the same topology. Language receives sensory events and fixed token codes and predicts the next symbol through a fixed readout. Held-out evaluation pairs original and order-reversed scenes with their corresponding equal-length descriptions. Orange marks the sensory-shuffle control used only at evaluation.

Endpoint	Anat.	Rewired	$\Delta$
Addition overall	92.77	67.93	+24.84
Addition carry ( $<100$ )	92.96	69.09	+23.88
Language factorial	61.59	44.17	+17.42
Language ensemble	71.35	46.56	+24.79

Table 1: Primary topology comparisons.

Figure 2: Bounded-addition results. (a) Held-out accuracy for four anatomical runs and eight runs on three degree-preserving rewires. Horizontal segments mark topology-class means. (b) Accuracy without and with a ones-digit carry among examples whose sum is below 100. Lines connect the two strata within each run. Sum-100 examples are reported separately in Appendix F .

Figure 3: Grounded relational language results. (a) Strict paired scores at the canonical interface I1 and three alternative placements. Each anatomical fit is compared with four rewires. Horizontal segments mark rewire means. (b) On the same 48 groups, sensory shuffling reduces the anatomical score from $60.94\%$ to $19.27\%$ and the rewire mean from $41.80\%$ to $13.02\%$ . The dotted line marks the $1/6$ chance reference.

Figure 4: Rewire ensemble at interface I1. The 20 degree-preserving rewire scores are sorted for display. The anatomical graph scores $71.35\%$ , above every rewire and the ensemble mean of $46.56\%$ . Its finite-ensemble rank fraction is $1/21$ . The dotted line marks the $1/6$ chance reference.

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Quantity	Value
Source-article neuron total	166,700 neurons
Source-article connected neurons	166,483 neurons
Selection	Superclass annotation assigned
Selected neurons in processed graph	166,700
Directed aggregated edges	25,582,938
Synaptic contacts represented	124,177,617

Appendix

Table 2: Processed graph and source statistics.

Component	Content
Question	What did I feel?
Original scene $r$	strong, long, slow pressure on the right middle leg; then weak, short, slow movement on the right front leg
Candidate $y$	The strong pressure on the right middle leg happened before the weak movement on the right front leg. The first signal started slowly and stopped after a long time. The last signal started slowly and stopped after a short time.
Reversed scene $r^{\leftrightarrow}$	weak, short, slow movement on the right front leg; then strong, long, slow pressure on the right middle leg
Candidate $y^{\leftrightarrow}$	The weak movement on the right front leg happened before the strong pressure on the right middle leg. The first signal started slowly and stopped after a short time. The last signal started slowly and stopped after a long time.

Appendix

Table 3: Worked example of a paired language group.

Signal kind	Rendered meaning	Rendered action
touch	a signal from the body	follow the signal
taste	food	approach the food
movement	a change in the ground	follow the movement
pressure	pain and danger	avoid that place

Appendix

Table 4: Authored signal conventions in the language generator.

Category	Words
Nouns	fly, body, leg, legs, side, strength, touch, taste, movement, pressure, signal, sensation, event, events, pain, food, ground, danger, place, time, pulse, change
Attributes	left, right, front, middle, hind, weak, strong, short, long, quickly, slowly, first, last, same, different, one, two, three, four
Verbs	feel, felt, detect, detected, happen, happened, start, started, stop, stopped, mean, meant, avoid, avoided, approach, approached, follow, followed, do
Function words	a, the, that, my, its, it, i, they, both, another, is, are, was, were, did, in, on, to, from, of, and, but, so, because, before, after, while, then, not, no, yes, what, where, when, which, why, how, many, there, or

Appendix

Table 5: The 100-word lexicon.

Mode	Count	Content
Report	2	First- and third-person descriptions of complete event sequences
Question answering	18	Event identity and attributes, temporal order, location, comparisons, counts, meaning, action, and causal explanation
Controlled text	11	Temporal and causal statements, contrasts, simultaneous events, counting, side descriptions, pulses, and short dialogue

Appendix

Table 6: Template families used by the deterministic corpus generator.

Diagnostic	Anatomical	20 rewires
Source-edge overlap (%)	100	0.591 [0.588, 0.594]
Accepted swaps per edge	0	5
Reciprocal directed edges (%)	29.893	0.517 [0.514, 0.520]
Largest SCC (% nodes)	99.169	99.176 [99.175, 99.176]
Token $\to$ output min. distance	1.507	1.506 [1.448, 1.546]
Sensory $\to$ output min. distance	2.552	1.378 [1.343, 1.412]

Appendix

Table 7: Structural diagnostics for the anatomical graph and rewired controls. Brackets give the minimum and maximum across 20 rewires.

Topology	Run	Overall	No carry	Carry	Sum 100	MAE
		(792)	(438)	(334)	(20)
Anatomical	1	97.22	96.80	97.60	100	0.078
Anatomical	2	95.96	96.12	95.51	100	0.110
Anatomical	3	99.12	98.86	99.40	100	0.040
Anatomical	4	78.79	78.54	79.34	75	0.266
Rewire 1	1	66.41	67.35	67.37	30	0.413

Appendix

Table 8: Every bounded-addition test run.

Interface	Anatomical	R1	R2	R3	R4	Rewire mean	$\Delta$
I1 (canonical)	71.35	38.02	58.85	42.71	40.10	44.92	26.43
I2	57.29	39.58	47.92	35.42	41.15	41.02	16.28
I3	61.46	50.52	51.04	35.42	47.40	46.09	15.36
I4	56.25	43.75	47.92	43.75	43.23	44.66	11.59
Mean	61.59	42.97	51.43	39.32	42.97	44.17	17.42

Appendix

Table 9: Every cell in the primary language factorial. R1–R4 denote the four prespecified rewired graphs.

Position	Score	Position	Score	Position	Score
1	36.98	8	42.71	15	51.56
2	38.02	9	44.27	16	54.17
3	39.06	10	44.79	17	55.21
4	39.06	11	46.88	18	55.73
5	40.10	12	47.40	19	57.81
6	40.10	13	47.92	20	58.85

Appendix

Table 10: I1 rewire scores, ordered from lowest to highest.

Topology	Run 1	Run 2	Run 3	Mean	SD
Anatomical	71.35	68.23	73.44	71.01	2.62
Rewire 1	38.02	55.73	45.83	46.53	8.87
Rewire 2	58.85	37.50	42.19	46.18	11.22

Appendix

Table 11: Strict paired scores at I1 across optimization runs.

	Anatomical		Rewire mean
Interface	Normal	Shuffled	Normal	Shuffled
I1	68.75	25.00	44.79	12.50
I2	56.25	18.75	39.58	13.02
I3	62.50	20.83	42.71	14.58
I4	56.25	12.50	40.10	11.98
Mean	60.94	19.27	41.80	13.02

Appendix

Table 12: Sensory intervention by interface. Normal and shuffled values use the same records; rewire entries average four graphs.

	Two-preference		Strict four-inequality
Factor	Anatomical	Rewired	Anatomical	Rewired
Strength	46.35	13.02	17.19	1.82
Duration	59.38	4.69	22.40	0.52
Speed	4.17	0.52	0.00	0.13
Order	26.56	16.41	26.04	16.28
Macro mean	34.11	8.66	16.41	4.69

Appendix

Table 13: Pair-preserving counterfactual accuracy by changed factor. Each factor uses 48 groups per run.

Run	Primary	Normal (48)	Shuffled (48)	Counterfactual
1	5.73	4.17	0.00	2.08
2	8.33	6.25	0.00	3.65
3	17.71	22.92	6.25	6.25
4	3.13	4.17	0.00	1.56
Mean	8.72	9.38	1.56	3.39

Appendix

Table 14: Dense-control results by optimization run. Primary, Normal, and Shuffled report strict paired accuracy. Counterfactual reports the two-preference macro accuracy over strength, duration, speed, and order. All values are percentages.

Explore similar work

Structure alone supports efficient visual computation in the Drosophila visual system
Oct 7, 2026Eudald Correig-Fraga, Roger Guimerà, Marta Sales-PardoVisual Perception
Innovamat Education, Sant Cugat del Vallès, Catalonia · Department of Chemical Engineering, Universitat Rovira i Virgili, Tarragona, Catalonia · Center for Computational Science and Applied Mathematics (ComSCIAM), Universitat Rovira i Virgili, Tarragona, Catalonia +1
Harnessing cortical geometry, wiring, and function as inductive biases for recurrent neural networks
Jun 12, 2026Mo Shakiba, Rana Rokni, Mohammad Mohammadi +1Neural Circuits Human Visual Cortex
Neuromatch Academy, Neuromatch, Inc., USA · McGovern Institute for Brain Research, Massachusetts Institute of Technology (MIT)
Null-model treatment of the sensory-motor boundary changes an evolutionary connectome comparison
Sep 30, 2026Gyujeong ParkHuman Connectome Project Connectome
IonLabs

Oct 7, 2026, q-bio.NCJ/K move · Enter open · S save

Structure alone supports efficient visual computation in the Drosophila visual system

Eudald Correig-Fraga, Roger Guimerà, Marta Sales-Pardo

Innovamat Education, Sant Cugat del Vallès, Catalonia · Department of Chemical Engineering, Universitat Rovira i Virgili, Tarragona, Catalonia · Center for Computational Science and Applied Mathematics (ComSCIAM), Universitat Rovira i Virgili, Tarragona, Catalonia+1

Visual Perception

Open paper AskPDF arXiv

Understanding the extent to which measured synaptic wiring determines computation remains a central challenge. Here, we couple the proofread adult Drosophila melanogaster connectome to an anatomically faithful model of its eye. Visual information is inputted in the eye model, then passed to the connectome, and finally read from a Kenyon-cell-centered linear decoder. This creates a connectome-only model in which the anatomical graph and eye geometry are fixed and only scalar synaptic gains and neuronal thresholds may be learned. The model supports multitask vision, including color discrimination, shape classification, and numerical discrimination that follows a ratio-dependent scaling characteristic of approximate number perception. To test whether precise connectivity is consequential under wiring economy, we compare the biological graph to randomized ensembles that increasingly preserve biological synaptic constraints. At matched wiring cost, the biological network consistently yields higher accuracy, whereas less constrained rewiring surpasses it at the cost of inflated wiring. These findings indicate that the measured connectivity and eye geometry jointly set efficient operating points for visual computation.

Abstract

Explore similar work

Structure alone supports efficient visual computation in the Drosophila visual system

Harnessing cortical geometry, wiring, and function as inductive biases for recurrent neural networks

Null-model treatment of the sensory-motor boundary changes an evolutionary connectome comparison