Skip to yearly menu bar Skip to main content


Using Fast Weights to Attend to the Recent Past

Jimmy Ba · Geoffrey E Hinton · Volodymyr Mnih · Joel Leibo · Catalin Ionescu

Area 5+6+7+8 #191

Keywords: [ (Cognitive/Neuroscience) Theoretical Neuroscience ] [ Deep Learning or Neural Networks ]


Until recently, research on artificial neural networks was largely restricted to systems with only two types of variable: Neural activities that represent the current or recent input and weights that learn to capture regularities among inputs, outputs and payoffs. There is no good reason for this restriction. Synapses have dynamics at many different time-scales and this suggests that artificial neural networks might benefit from variables that change slower than activities but much faster than the standard weights. These ``fast weights'' can be used to store temporary memories of the recent past and they provide a neurally plausible way of implementing the type of attention to the past that has recently proven helpful in sequence-to-sequence models. By using fast weights we can avoid the need to store copies of neural activity patterns.

Live content is unavailable. Log in and register to view live content