Mistake gating leads to energy and memory efficient continual learning

Synaptic plasticity is metabolically expensive, yet animals continuously update their internal models without exhausting energy reserves. However, when artificial neural networks are trained, the network parameters are typically updated on every sample that is presented, even if the sample was classified correctly. Inspired by the human negativity bias and error-related negativity, we propose 'memorized mistake-gated learning' -- a biologically plausible plasticity rule where synaptic updates are strictly gated by current and past classification errors. This reduces the number of updates the network needs to make by $50\%\sim80\%$. Mistake gating is particularly well suited in two cases: 1) For incremental learning where new knowledge is acquired on a background of pre-existing knowledge, 2) For online learning scenarios when data needs to be stored for later replay, as mistake-gating reduces storage buffer requirements. The algorithm can be implemented in a few lines of code, adds no hyper-parameters, and comes at negligible computational overhead. Learning on mistakes is an energy efficient and biologically relevant modification to commonly used learning rules that is well suited for continual learning.

Competitive plasticity to reduce the energetic costs of learning

The brain is not only constrained by energy needed to fuel computation, but it is also constrained by energy needed to form memories. Experiments have shown that learning simple conditioning tasks already carries a significant metabolic cost. Yet, learning a task like MNIST to 95% accuracy appears to require at least 10^{8} synaptic updates. Therefore the brain has likely evolved to be able to learn using as little energy as possible. We explored the energy required for learning in feedforward neural networks. Based on a parsimonious energy model, we propose two plasticity restricting algorithms that save energy: 1) only modify synapses with large updates, and 2) restrict plasticity to subsets of synapses that form a path through the network. Combining these two methods leads to substantial energy savings while only incurring a small increase in learning time. In biology networks are often much larger than the task requires. In particular in that case, large savings can be achieved. Thus competitively restricting plasticity helps to save metabolic energy associated to synaptic plasticity. The results might lead to a better understanding of biological plasticity and a better match between artificial and biological learning. Moreover, the algorithms might also benefit hardware because in electronics memory storage is energetically costly as well.

Lazy learning: a biologically-inspired plasticity rule for fast and energy efficient synaptic plasticity

When training neural networks for classification tasks with backpropagation, parameters are updated on every trial, even if the sample is classified correctly. In contrast, humans concentrate their learning effort on errors. Inspired by human learning, we introduce lazy learning, which only learns on incorrect samples. Lazy learning can be implemented in a few lines of code and requires no hyperparameter tuning. Lazy learning achieves state-of-the-art performance and is particularly suited when datasets are large. For instance, it reaches 99.2% test accuracy on Extended MNIST using a single-layer MLP, and does so 7.6x faster than a matched backprop network

Estimating the energy requirements for long term memory formation

Brains consume metabolic energy to process information, but also to store memories. The energy required for memory formation can be substantial, for instance in fruit flies memory formation leads to a shorter lifespan upon subsequent starvation (Mery and Kawecki, 2005). Here we estimate that the energy required corresponds to about 10mJ/bit and compare this to biophysical estimates as well as energy requirements in computer hardware. We conclude that biological memory storage is expensive, but the reason behind it is not known.