Modular　neural　network　is　an　effective　method　to　solve　the　complex　problems　that　the　monolithic　fully　coupled　feedforward　neural　networks　are　difficult　to　learn.　The　most　difficult　problem　of　the　modular　neural　network　design　method　now　facing　is　how　to　determine　the　number　of　function　modules　and　the　structure　of　the　sub-modules　in　each　function　module　under　the　condition　of　lack　of　the　learned　objects　back　ground　knowledge.　In　this　paper,　we　presents　a　hierarchical　adaptive　modular　neural　network　structure　design　method　based　on　the　facts　that　the　brain-like　information　process　uses　the　mechanism　of　unsupervised　learning,　semi-supervised　learning　and　supervised　learning,　and　the　brain　networks　demonstrate　the　property　of　hierarchical　modularity,　within　each　module　there　will　be　a　set　of　function　modules,　and　within　each　function　there　will　be　a　set　of　sub-modules,　and　the　brain-like　information　learning　processing　is　purposeful　to　select　several　sub-modules　from　different　function　module　to　collaboratively　learning.　In　essence,　firstly,　an　unsupervised　clustering　algorithm　named　fast　finding　of　density　peaks　cluster　algorithm　is　adopted　to　identify　the　cluster　centers　based　on　all　training　samples,　then　the　number　of　the　function　module　and　the　training　set　of　each　function　module　can　be　determined.　Secondly,　a　semi-supervised　clustering　algorithm　named　conditional　fuzzy　clustering　algorithm　is　used　to　divide　the　training　set　of　each　function　module　into　several　groups　to　determine　the　number　of　sub-modules　in　each　function　module.　For　each　sub-module,　an　incremental　design　of　RBF　network　algorithm　based　on　training　error　peak　is　applied　to　construct　the　structure　of　sub-module,　this　algorithm　can　adaptively　build　the　structure　of　the　sub-modules　based　on　the　training　samples　that　allocated　to　the　sub-modules.　In　sub-modules　integration,　a　sub-module　integrative　approach　based　on　relative　distance　measure　is　applied　which　can　select　different　sub-modules　from　different　function　modules　to　collaboratively　learning　the　training　samples.　The　modular　neural　network　structure　design　method　we　presented　in　this　paper　solves　the　problem　of　how　to　determine　the　number　of　sub-modules　and　the　structure　of　the　sub-modules　on　the　situation　of　lack　of　the　back　ground　knowledge　of　the　learning　objects,　moreover,　the　presented　modular　neural　network　design　method　requires　only　2　artificial　parameters　(Hi　the　number　of　sub-modules　in　each　function　module,　K　the　membership　degree　of　training　samples　to　function　module　training　sets)　compared　with　other　modular　neural　network　design　methods,　and　the　learning　speed　increased　nearly　by　10　times　compared　with　monolithic　fully　coupled　RBF　neural　network,　therefore,　the　proposed　modular　neural　design　method　really　achieves　the　black　box　effect　on　neural　network　application.　At　the　end　of　this　paper,　we　evaluate　the　proposed　hierarchical　modular　neural　network　on　several　benchmark　problems,　include　complex　function　fitting　problem　and　double　helix　classification　problem　based　on　artificial　data　set,　and　complex　data　regression　problems　based　on　real　data　sets.　The　extensive　results　show　that　the　modular　neural　network　architecture　proposed　in　this　paper　can　not　only　solve　the　complex　problems　that　the　fully　coupled　RBF　difficult　to　deal　with,　but　also　has　high　learning　precision,　fast　learning　speed　and　high　generalization　ability.　©　2017,　Science　Press.　All　right　reserved.