More Like this

1. Reward-based training of recurrent neural networks for cognitive and value-based tasks

   https://doi.org/10.7554/eLife.21492  

   Song, H Francis ; Yang, Guangyu R ; Wang, Xiao-Jing ( January 2017 , eLife)

   A major goal in neuroscience is to understand the relationship between an animal’s behavior and how this is encoded in the brain. Therefore, a typical experiment involves training an animal to perform a task and recording the activity of its neurons – brain cells – while the animal carries out the task. To complement these experimental results, researchers “train” artificial neural networks – simplified mathematical models of the brain that consist of simple neuron-like units – to simulate the same tasks on a computer. Unlike real brains, artificial neural networks provide complete access to the “neural circuits” responsible for a behavior, offering a way to study and manipulate the behavior in the circuit. One open issue about this approach has been the way in which the artificial networks are trained. In a process known as reinforcement learning, animals learn from rewards (such as juice) that they receive when they choose actions that lead to the successful completion of a task. By contrast, the artificial networks are explicitly told the correct action. In addition to differing from how animals learn, this limits the types of behavior that can be studied using artificial neural networks. Recent advances in the field of machinemore »learning that combine reinforcement learning with artificial neural networks have now allowed Song et al. to train artificial networks to perform tasks in a way that mimics the way that animals learn. The networks consisted of two parts: a “decision network” that uses sensory information to select actions that lead to the greatest reward, and a “value network” that predicts how rewarding an action will be. Song et al. found that the resulting artificial “brain activity” closely resembled the activity found in the brains of animals, confirming that this method of training artificial neural networks may be a useful tool for neuroscientists who study the relationship between brains and behavior. The training method explored by Song et al. represents only one step forward in developing artificial neural networks that resemble the real brain. In particular, neural networks modify connections between units in a vastly different way to the methods used by biological brains to alter the connections between neurons. Future work will be needed to bridge this gap.« less
2. Task-Driven convolutional recurrent models of the visual system.

   Nayebi, A ; Bear, D ; Kubilius, J ; Kar, K ; Ganguli, S ; Sussillo, D ; DiCarlo, JJ ; Yamins, DL. ( July 2018 , Advances in Neural Information Processing Systems 2018)

   Feed-forward convolutional neural networks (CNNs) are currently state-of-the-art for object classification tasks such as ImageNet. Further, they are quantitatively accurate models of temporally-averaged responses of neurons in the primate brain's visual system. However, biological visual systems have two ubiquitous architectural features not shared with typical CNNs: local recurrence within cortical areas, and long-range feedback from downstream areas to upstream areas. Here we explored the role of recurrence in improving classification performance. We found that standard forms of recurrence (vanilla RNNs and LSTMs) do not perform well within deep CNNs on the ImageNet task. In contrast, novel cells that incorporated two structural features, bypassing and gating, were able to boost task accuracy substantially. We extended these design principles in an automated search over thousands of model architectures, which identified novel local recurrent cells and long-range feedback connections useful for object recognition. Moreover, these task-optimized ConvRNNs matched the dynamics of neural activity in the primate visual system better than feedforward networks, suggesting a role for the brain's recurrent connections in performing difficult visual behaviors.
3. Encoding time in neural dynamic regimes with distinct computational tradeoffs

   https://doi.org/10.1371/journal.pcbi.1009271  

   Zhou, Shanglin ; Masmanidis, Sotiris C. ; Buonomano, Dean V. ( March 2022 , PLOS Computational Biology)

   Gutkin, Boris S. (Ed.)

   Converging evidence suggests the brain encodes time in dynamic patterns of neural activity, including neural sequences, ramping activity, and complex dynamics. Most temporal tasks, however, require more than just encoding time, and can have distinct computational requirements including the need to exhibit temporal scaling, generalize to novel contexts, or robustness to noise. It is not known how neural circuits can encode time and satisfy distinct computational requirements, nor is it known whether similar patterns of neural activity at the population level can exhibit dramatically different computational or generalization properties. To begin to answer these questions, we trained RNNs on two timing tasks based on behavioral studies. The tasks had different input structures but required producing identically timed output patterns. Using a novel framework we quantified whether RNNs encoded two intervals using either of three different timing strategies: scaling, absolute, or stimulus-specific dynamics. We found that similar neural dynamic patterns at the level of single intervals, could exhibit fundamentally different properties, including, generalization, the connectivity structure of the trained networks, and the contribution of excitatory and inhibitory neurons. Critically, depending on the task structure RNNs were better suited for generalization or robustness to noise. Further analysis revealed different connection patterns underlyingmore »the different regimes. Our results predict that apparently similar neural dynamic patterns at the population level (e.g., neural sequences) can exhibit fundamentally different computational properties in regards to their ability to generalize to novel stimuli and their robustness to noise—and that these differences are associated with differences in network connectivity and distinct contributions of excitatory and inhibitory neurons. We also predict that the task structure used in different experimental studies accounts for some of the experimentally observed variability in how networks encode time.« less
4. Analyzing Emergence in Biological Neural Networks Using Graph Signal Processing

   https://doi.org/10.1201/9781003160816-10  

   Schultz, Kevin ; Villafañe-Delgado, Marisel ; Reilly, Elizabeth P. ; Saksena, Anshu ; Hwang, Grace M. ( January 2022 , Emergent Behavior in System of Systems Engineering)

   Rainey, Larry B. ; Holland, O. Thomas (Ed.)

   Biological neural networks offer some of the most striking and complex examples of emergence ever observed in natural or man-made systems. Individually, the behavior of a single neuron is rather simple, yet these basic building blocks are connected through synapses to form neural networks, which are capable of sophisticated capabilities such as pattern recognition and navigation. Lower-level functionality provided by a given network is combined with other networks to produce more sophisticated capabilities. These capabilities manifest emergently at two vastly different, yet interconnected time scales. At the time scale of neural dynamics, neural networks are responsible for turning noisy external stimuli and internal signals into signals capable of supporting complex computations. A key component in this process is the structure of the network, which itself forms emergently over much longer time scales based on the outputs of its constituent neurons, a process called learning. The analysis and interpretation of the behaviors of these interconnected dynamical systems of neurons should account for the network structure and the collective behavior of the network. The field of graph signal processing (GSP) combines signal processing with network science to study signals defined on irregular network structures. Here, we show that GSP can be amore »valuable tool in the analysis of emergence in biological neural networks. Beyond any purely scientific pursuits, understanding the emergence in biological neural networks directly impacts the design of more effective artificial neural networks for general machine learning and artificial intelligence tasks across domains, and motivates additional design motifs for novel emergent systems of systems.« less
5. Similarity Learning and Generalization with Limited Data: A Reservoir Computing Approach

   https://doi.org/10.1155/2018/6953836  

   Krishnagopal, Sanjukta ; Aloimonos, Yiannis ; Girvan, Michelle ( November 2018 , Complexity)

   We investigate the ways in which a machine learning architecture known as Reservoir Computing learns concepts such as “similar” and “different” and other relationships between image pairs and generalizes these concepts to previously unseen classes of data. We present two Reservoir Computing architectures, which loosely resemble neural dynamics, and show that a Reservoir Computer (RC) trained to identify relationships between image pairs drawn from a subset of training classes generalizes the learned relationships to substantially different classes unseen during training. We demonstrate our results on the simple MNIST handwritten digit database as well as a database of depth maps of visual scenes in videos taken from a moving camera. We consider image pair relationships such as images from the same class; images from the same class with one image superposed with noise, rotated 90°, blurred, or scaled; images from different classes. We observe that the reservoir acts as a nonlinear filter projecting the input into a higher dimensional space in which the relationships are separable; i.e., the reservoir system state trajectories display different dynamical patterns that reflect the corresponding input pair relationships. Thus, as opposed to training in the entire high-dimensional reservoir space, the RC only needs to learns characteristicmore »features of these dynamical patterns, allowing it to perform well with very few training examples compared with conventional machine learning feed-forward techniques such as deep learning. In generalization tasks, we observe that RCs perform significantly better than state-of-the-art, feed-forward, pair-based architectures such as convolutional and deep Siamese Neural Networks (SNNs). We also show that RCs can not only generalize relationships, but also generalize combinations of relationships, providing robust and effective image pair classification. Our work helps bridge the gap between explainable machine learning with small datasets and biologically inspired analogy-based learning, pointing to new directions in the investigation of learning processes.« less