Attractor Network Dynamics Enable Preplay and Rapid Path Planning in Maze–like Environments

Rodents navigating in a well-known environment can rapidly learn and revisit observed reward locations, often after a single trial. While the mechanism for rapid path planning is unknown, the CA3 region in the hippocampus plays an important role, and emerging evidence suggests that place cell activity during hippocampal preplay periods may trace out future goal-directed trajectories. Here, we show how a particular mapping of space allows for the immediate generation of trajectories between arbitrary start and goal locations in an environment, based only on the mapped representation of the goal. We show that this representation can be implemented in a neural attractor network model, resulting in bump--like activity profiles resembling those of the CA3 region of hippocampus. Neurons tend to locally excite neurons with similar place field centers, while inhibiting other neurons with distant place field centers, such that stable bumps of activity can form at arbitrary locations in the environment. The network is initialized to represent a point in the environment, then weakly stimulated with an input corresponding to an arbitrary goal location. We show that the resulting activity can be interpreted as a gradient ascent on the value function induced by a reward at the goal location. Indeed, in networks with large place fields, we show that the network properties cause the bump to move smoothly from its initial location to the goal, around obstacles or walls. Our results illustrate that an attractor network with hippocampal-like attributes may be important for rapid path planning.

Model-based reinforcement learning and navigation in animals and machines

Dane Sterling Corneil

For decades, neuroscientists and psychologists have observed that animal performance on spatial navigation tasks suggests an internal learned map of the environment. More recently, map-based (or model-based) reinforcement learning has become a highly active research area in machine learning. With a learned model of their environment, both animals and artificial agents can generalize between tasks and learn rapidly. In this thesis, I present approaches for developing efficient model--based behaviour in machines and explaining model--based behaviour in animals. From a neuroscience perspective, I focus on the hippocampus, believed to be a major substrate of model-based behaviour in the brain. I consider how hippocampal connectivity enable path--finding between different locations in an environment. The model describes how environments with boundaries and barriers can be represented in recurrent neural networks (i.e. attractor networks), and how the transient activity in these networks, after being stimulated with a goal location, could be used for determining a path to the goal. I also propose how the connectivity of these map--like networks can be learned from the spatial firing patterns observed in the input pathway to the hippocampus (i.e. grid cells and border cells). From a machine learning perspective, I describe a reinforcement learning model that integrates model-based methods and "episodic control", an approach to reinforcement learning based on episodic memory. According to episodic control, the agent learns how to act in the environment by storing snapshot-like memories of its observations, then comparing its current observations to similar snapshot memories where it took an action that resulted in high reward. In our approach, the agent augments these real-world memories with episodes simulated offline using a learned model of the environment. These ``simulated memories'' allow the agent to adapt faster when the reward locations change. Next, I describe Variational State Tabulation (VaST), a model--based method for learning quickly with continuous and high-dimensional observations (like those found in 3D navigation tasks). The VaST agent learns to map its observations to a limited number of discrete abstract states, and build a transition model over those abstract states. The long--term values of different actions in each state are updated continuously and efficiently in the background as the agent explores the environment. I show how the VaST agent can learn faster than other state-of-the-art algorithms, even changing its policy after a single new experience, and how it can respond quickly to changing rewards in complex 3D environments. The models I present allow the agent to rapidly adapt to changing goals and rewards, a key component of intelligence. They use a combination of features attributed to model-based and episodic controllers, suggesting that the division between the two fields is not strict. I therefore also consider the consequences of these findings on theories of model-based learning, episodic control and hippocampal function.

EPFL2018

Music Learning with Long Short Term Memory Networks

Florian François Colombo

Humans are able to learn and compose complex, yet beautiful, pieces of music as seen in e.g. the highly complicated works of J.S. Bach. However, how our brain is able to store and produce these very long temporal sequences is still an open question. Long short-term memory (LSTM) artificial neural networks have been shown to be efficient in sequence learning tasks thanks to their inherent ability to bridge long time lags between input events and their target signals. Here, I investigate the possibility of training LSTM networks to learn and reproduce musical sequences and eventually better understand some of the mechanisms neural networks deploy to learn and compose long time scale structures. To be able to learn music with LSTM networks requires representing musical sequences in these networks. The musical representation developed for this work is inspired by the tonotopic representation of sounds in the auditory system. It is shown that LSTM networks are able to learn each note transitions of the monophonic and polyphonic versions of a simple song using a particular network architecture where both input and output of LSTM networks are musical notes in the developed network representation. However, this architecture for LSTM networks fail to learn longer and more complex musical sequences (e.g. the J.S. Bach cello suites). To solve this problem, I introduce the separation of time scales model, which consists in two connected LSTM networks, operating on different time scales. On one hand, trained slow time scale LSTM networks produce transitions between unique identifiers of musical patterns, which resemble a compressed memory of the pattern akin to neural memory. This gives the long time structure of music. On the other hand, trained fast time scale LSTM networks are producing the note-to-note transitions of each musical patterns. The latter receives as additional inputs the identifiers from slow time scale networks, akin to feed- forward input from memory regions of the brain. These unique identifiers bias fast time scale LSTM networks toward the production of the corresponding musical pattern. The most efficient identifiers of musical patterns are found to be a representation of how similar patterns are from one another. Finally, when unlearned pattern identifiers are given to trained fast time scale networks, novel musical patterns are created from the learned production rules. I show that the introduction of a separation of time scales greatly improves the capacity of LSTM networks to learn a larger body of musical sequences. Finally, I demonstrate that previously unseen input biases can be used to induce the network into the generation of new musical sequences, akin but not similar to known patterns. This presents a possible first step towards the generalization of previously learnt musical knowledge to the creation and composition of new music by artificial neural networks.

2015

OrthoNet: Multilayer Network Data Clustering

Giovanni Chierchia, Mireille El Gheche, Pascal Frossard

Network data appears in very diverse applications, like biological, social, or sensor networks. Clustering of network nodes into categories or communities has thus become a very common task in machine learning and data mining. Network data comes with some information about the network edges. In some cases, this network information can even be given with multiple views or layers, each one representing a different type of relationship between the network nodes. Increasingly often, network nodes also carry a feature vector. We propose in this paper to extend the node clustering problem, that commonly considers only the network information, to a problem where both the network information and the node features are considered together for learning a clustering-friendly representation of the feature space. Specifically, we design a generic two-step algorithm for multilayer network data clustering. The first step aggregates the different layers of network information into a graph representation given by the geometric mean of the network Laplacian matrices. The second step uses a neural net to learn a feature embedding that is consistent with the structure given by the network layers. We propose a novel algorithm for efficiently training the neural net via gradient descent, which encourages the neural net outputs to span the leading eigenvectors of the aggregated Laplacian matrix, in order to capture the pairwise interactions on the network, and provide a clustering-friendly representation of the feature space. We demonstrate with an extensive set of experiments on synthetic and real datasets that our method leads to a significant improvement w.r.t. state-of-the-art multilayer graph clustering algorithms, as it judiciously combines nodes features and network information in the node embedding algorithms.