In　this　paper,　we　propose　a　deep　neural　network-based　car-following　model　that　has　two　distinctive　properties.　First,　unlike　most　existing　car-following　models　that　take　only　the　instantaneous　velocity,　velocity　difference,　and　position　difference　as　inputs,　this　new　model　takes　the　velocities,　velocity　differences,　and　position　differences　that　were　observed　in　the　last　few　time　intervals　as　inputs.　That　is,　we　assume　that　drivers＇　actions　are　temporally　dependent　in　this　model　and　try　to　embed　prediction　capability　or　memory　effect　of　human　drivers　in　a　natural　and　efficient　way.　Second,　this　car-following　model　is　built　in　a　data-driven　way,　in　which　we　reduce　human　interference　to　the　minimum　degree.　Specially,　we　use　recently　developing　deep　neural　networks　rather　than　conventional　neural　networks　to　establish　the　model,　since　deep　learning　technique　provides　us　more　flexibility　and　accuracy　to　describe　complicated　human　actions.　Tests　on　empirical　trajectory　records　show　that　this　deep　neural　network-based　car-following　model　yield　significantly　higher　simulation　accuracy　than　existing　car-following　models.　All　these　findings　provide　a　novel　way　to　study　traffic　flow　theory　and　traffic　simulations.