We propose a novel biologically-plausible solution to the credit assignment problem, being motivated by observations in the ventral visual pathway and trained deep neural networks. In both, representations of objects in the same category become progressively more similar, while objects belonging to different categories becomes less similar. We use this observation to motivate a layer-specific learning goal in a deep network: each layer aims to learn a representational similarity matrix that interpolates between previous and later layers. We formulate this idea using a supervised deep similarity matching cost function and derive from it deep neural networks with feedforward, lateral and feedback connections, and neurons that exhibit biologically-plausible Hebbian and anti-Hebbian plasticity. Supervised deep similarity matching can be interpreted as an energy-based learning algorithm, but with significant differences from others in how a contrastive function is constructed.
How can we build agents that keep learning from experience, quickly and efficiently, after their initial training? Here we take inspiration from the main mechanism of learning in biological brains: synaptic plasticity, carefully tuned by evolution to produce efficient lifelong learning. We show that plasticity, just like connection weights, can be optimized by gradient descent in large (millions of parameters) recurrent networks with Hebbian plastic connections. First, recurrent plastic networks with more than two million parameters can be trained to memorize and reconstruct sets of novel, high-dimensional 1000+ pixels natural images not seen during training. Crucially, traditional non-plastic recurrent networks fail to solve this task. Furthermore, trained plastic networks can also solve generic meta-learning tasks such as the Omniglot task, with competitive results and little parameter overhead. Finally, in reinforcement learning settings, plastic networks outperform a non-plastic equivalent in a maze exploration task. We conclude that differentiable plasticity may provide a powerful novel approach to the learning-to-learn problem.
Biological plastic neural networks are systems of extraordinary computational capabilities shaped by evolution, development, and lifetime learning. The interplay of these elements leads to the emergence of adaptive behavior and intelligence. Inspired by such intricate natural phenomena, Evolved Plastic Artificial Neural Networks (EPANNs) use simulated evolution in-silico to breed plastic neural networks with a large variety of dynamics, architectures, and plasticity rules: these artificial systems are composed of inputs, outputs, and plastic components that change in response to experiences in an environment. These systems may autonomously discover novel adaptive algorithms, and lead to hypotheses on the emergence of biological adaptation. EPANNs have seen considerable progress over the last two decades. Current scientific and technological advances in artificial neural networks are now setting the conditions for radically new approaches and results. In particular, the limitations of hand-designed networks could be overcome by more flexible and innovative solutions. This paper brings together a variety of inspiring ideas that define the field of EPANNs. The main methods and results are reviewed. Finally, new opportunities and developments are presented.
Columbia University is learning how to build and train self-aware neural networks, systems that can adapt and improve by using internal simulations and knowledge of their own structures. The University of California, Irvine, is studying the dual memory architecture of the hippocampus and cortex to replay relevant memories in the background, allowing the systems to become more adaptable and predictive while retaining previous learning. Tufts University is examining an intercellular regeneration mechanism observed in lower animals such as salamanders to create flexible robots capable of adapting to changes in their environment by altering their structures and functions on the fly. SRI International is developing methods to use environmental signals and their relevant context to represent goals in a fluid way rather than as discrete tasks, enabling AI agents to adapt their behavior on the go.
Humans and animals have the ability to continually acquire and fine-tune knowledge throughout their lifespan. This ability is mediated by a rich set of neurocognitive functions that together contribute to the early development and experience-driven specialization of our sensorimotor skills. Consequently, the ability to learn from continuous streams of information is crucial for computational learning systems and autonomous agents (inter)acting in the real world. However, continual lifelong learning remains a long-standing challenge for machine learning and neural network models since the incremental acquisition of new skills from non-stationary data distributions generally leads to catastrophic forgetting or interference. This limitation represents a major drawback also for state-of-the-art deep neural network models that typically learn representations from stationary batches of training data, thus without accounting for situations in which the number of tasks is not known a priori and the information becomes incrementally available over time. In this review, we critically summarize the main challenges linked to continual lifelong learning for artificial learning systems and compare existing neural network approaches that alleviate, to different extents, catastrophic interference. Although significant advances have been made in domain-specific continual lifelong learning with neural networks, extensive research efforts are required for the development of general-purpose artificial intelligence and autonomous agents. We discuss well-established research and recent methodological trends motivated by experimentally observed lifelong learning factors in biological systems. Such factors include principles of neurosynaptic stability-plasticity, critical developmental stages, intrinsically motivated exploration, transfer learning, and crossmodal integration.