Networks that learn the precise timing of event sequences

Veliz-Cuba, Alan; Shouval, Harel Z.; Josić, Krešimir; Kilpatrick, Zachary P.

doi:10.1007/s10827-015-0574-4

Cited by 26 publications

(26 citation statements)

References 94 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RNNs successfully solve machine learning tasks, such as natural language processing [3] and translation, [4] and composing music, [5] to name only a few domains. In particular, much of this success has been achieved by the use of recurrent networks of LSTM (long short-term memory) cells, first introduced by Hochreiter and Schmidhuber in 1997.…”

Section: Introductionmentioning

confidence: 99%

Generative Recurrent Networks for De Novo Drug Design

Gupta

Müller²,

Huisman³

et al. 2017

Molecular Informatics

437

418

View full text Add to dashboard Cite

Generative artificial intelligence models present a fresh approach to chemogenomics and de novo drug design, as they provide researchers with the ability to narrow down their search of the chemical space and focus on regions of interest. We present a method for molecular de novo design that utilizes generative recurrent neural networks (RNN) containing long short‐term memory (LSTM) cells. This computational model captured the syntax of molecular representation in terms of SMILES strings with close to perfect accuracy. The learned pattern probabilities can be used for de novo SMILES generation. This molecular design concept eliminates the need for virtual compound library enumeration. By employing transfer learning, we fine‐tuned the RNN′s predictions for specific molecular targets. This approach enables virtual compound design without requiring secondary or external activity prediction, which could introduce error or unwanted bias. The results obtained advocate this generative RNN‐LSTM system for high‐impact use cases, such as low‐data drug discovery, fragment based molecular design, and hit‐to‐lead optimization for diverse drug targets.

show abstract

Section: Introductionmentioning

confidence: 99%

Generative Recurrent Networks for De Novo Drug Design

Gupta

Müller²,

Huisman³

et al. 2017

Molecular Informatics

437

418

View full text Add to dashboard Cite

show abstract

“…Previous models have shown that neural activity sequences can emerge from initially unstructured networks of excitatory neurons via spike-timing-dependent plasticity (STDP) (Fiete et al, 2010; Veliz-Cuba et al, 2015; Ravid Tannenbaum and Burak, 2016). Compared with these earlier works, our model has the advantage of being able to dynamically adjust the speed of the activity sequence, as shown in Figure 4e ( cf .…”

Section: Resultsmentioning

confidence: 99%

“…however Refs. [Veliz-Cuba et al, 2015; Pehlevan et al, 2015; Tristan et al, 2014], where some temporal rescaling in activity patterns has been obtained using distinct mechanisms). In addition, our model does not require the assumption of heterosynaptic competition limiting the summed synaptic weights into and out of each unit, as in Ref.…”

Section: Resultsmentioning

confidence: 99%

“…Such a model should facilitate temporal rescaling and extrapolation to new speeds, flexibly change in order to meet changing contexts or behavioral goals, and decouple learning from performance. Several mechanisms have been proposed for generating sparse sequences, for example continuous attractor models (Rokni and Sompolinsky, 2012), reservoir computing networks (Rajan et al, 2016), and feedforward excitatory architectures including synfire chains (Abeles, 1991; Goldman, 2009; Fiete et al, 2010; Veliz-Cuba et al, 2015). Each of these models suffers limitations, however.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning multiple variable-speed sequences in striatum via cortical tutoring

Murray

Escola

2017

eLife

View full text Add to dashboard Cite

Sparse, sequential patterns of neural activity have been observed in numerous brain areas during timekeeping and motor sequence tasks. Inspired by such observations, we construct a model of the striatum, an all-inhibitory circuit where sequential activity patterns are prominent, addressing the following key challenges: (i) obtaining control over temporal rescaling of the sequence speed, with the ability to generalize to new speeds; (ii) facilitating flexible expression of distinct sequences via selective activation, concatenation, and recycling of specific subsequences; and (iii) enabling the biologically plausible learning of sequences, consistent with the decoupling of learning and execution suggested by lesion studies showing that cortical circuits are necessary for learning, but that subcortical circuits are sufficient to drive learned behaviors. The same mechanisms that we describe can also be applied to circuits with both excitatory and inhibitory populations, and hence may underlie general features of sequential neural activity pattern generation in the brain.DOI: http://dx.doi.org/10.7554/eLife.26084.001

show abstract

“…In models with supervised plasticity rules, the synapses are updated according the activity of the network and an error signal that carries information about the difference between the current network dynamics and the one that it is expected to learn by the network (Sussillo and Abbott, 2009;Laje and Buonomano, 2013;Memmesheimer et al, 2014;Rajan et al, 2016). In models with unsupervised plasticity rules, sequential dynamics is shaped by external stimulation without an error signal (Jun and Jin, 2007;Liu and Buonomano, 2009;Fiete et al, 2010;Waddington et al, 2012;Okubo et al, 2015;Veliz-Cuba et al, 2015). In those models SA is generated spontaneously, and the temporal statistics of the stimulation shapes the specific timing of the sequences.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Learning of Persistent and Sequential Activity

Pereira

Brunel

2020

Front. Comput. Neurosci.

View full text Add to dashboard Cite

Two strikingly distinct types of activity have been observed in various brain structures during delay periods of delayed response tasks: Persistent activity (PA), in which a sub-population of neurons maintains an elevated firing rate throughout an entire delay period; and Sequential activity (SA), in which sub-populations of neurons are activated sequentially in time. It has been hypothesized that both types of dynamics can be "learned" by the relevant networks from the statistics of their inputs, thanks to mechanisms of synaptic plasticity. However, the necessary conditions for a synaptic plasticity rule and input statistics to learn these two types of dynamics in a stable fashion are still unclear. In particular, it is unclear whether a single learning rule is able to learn both types of activity patterns, depending on the statistics of the inputs driving the network. Here, we first characterize the complete bifurcation diagram of a firing rate model of multiple excitatory populations with an inhibitory mechanism, as a function of the parameters characterizing its connectivity. We then investigate how an unsupervised temporally asymmetric Hebbian plasticity rule shapes the dynamics of the network. Consistent with previous studies, we find that for stable learning of PA and SA, an additional stabilization mechanism is necessary. We show that a generalized version of the standard multiplicative homeostatic plasticity (Renart et al., 2003; Toyoizumi et al., 2014) stabilizes learning by effectively masking excitatory connections during stimulation and unmasking those connections during retrieval. Using the bifurcation diagram derived for fixed connectivity, we study analytically the temporal evolution and the steady state of the learned recurrent architecture as a function of parameters characterizing the external inputs. Slow changing stimuli lead to PA, while fast changing stimuli lead to SA. Our network model shows how a network with plastic synapses can stably and flexibly learn PA and SA in an unsupervised manner.

show abstract

Networks that learn the precise timing of event sequences

Cited by 26 publications

References 94 publications

Generative Recurrent Networks for De Novo Drug Design

Generative Recurrent Networks for De Novo Drug Design

Learning multiple variable-speed sequences in striatum via cortical tutoring

Unsupervised Learning of Persistent and Sequential Activity

Contact Info

Product

Resources

About