no code implementations • 26 Apr 2023 • Takayuki Katsuki, Takayuki Osogami
This leads to a bias toward lower values in labels and the resultant learning because labels may have lower values due to incomplete observations, even if the actual magnitude of the phenomenon was high.
no code implementations • 8 Jul 2022 • Nicolò Cesa-Bianchi, Tommaso Cesari, Takayuki Osogami, Marco Scarsini, Segev Wasserkrug
We study a repeated game between a supplier and a retailer who want to maximize their respective profits without full knowledge of the problem parameters.
no code implementations • 28 Jan 2022 • Hiroshi Kajino, Kohei Miyaguchi, Takayuki Osogami
We are interested in in silico evaluation methodology for molecular optimization methods.
no code implementations • 15 Dec 2020 • Takayuki Osogami
We provide complete proofs of the lemmas about the properties of the regularized loss function that is used in the second order techniques for learning time-series with structural breaks in Osogami (2021).
no code implementations • 14 Nov 2019 • Takayuki Osogami
Here, we provide a supplementary material for Takayuki Osogami, "Uncorrected least-squares temporal difference with lambda-return," which appears in {\it Proceedings of the 34th AAAI Conference on Artificial Intelligence} (AAAI-20).
no code implementations • 2 Jul 2019 • Kun Zhao, Takayuki Osogami, Tetsuro Morimura
To solve this problem, we consider a whole match as a Markov chain of significant events, so that event values can be estimated with a continuous parameter space by solving the Markov chain with a machine learning model.
no code implementations • 28 Feb 2019 • Takayuki Osogami, Toshihiro Takahashi
Autonomous agents need to make decisions in a sequential manner, under partially observable environment, and in consideration of how other agents behave.
no code implementations • 6 Dec 2018 • Takayuki Katsuki, Takayuki Osogami, Akira Koseki, Masaki Ono, Michiharu Kudo, Masaki Makino, Atsushi Suzuki
This paper proposes a method for modeling event sequences with ambiguous timestamps, a time-discounting convolution.
no code implementations • 17 Dec 2017 • Rudy Raymond, Takayuki Osogami, Sakyasingha Dasgupta
Gaussian DyBM is a DyBM that assumes the predicted data is generated by a Gaussian distribution whose first-order moment (mean) dynamically changes over time but its second-order moment (variance) is fixed.
1 code implementation • 20 Aug 2017 • Takayuki Osogami
We review Boltzmann machines and energy-based models.
no code implementations • 20 Aug 2017 • Takayuki Osogami
We then review dynamic Boltzmann machines (DyBMs), whose learning rule is local in time.
no code implementations • ICML 2017 • Takayuki Osogami, Hiroshi Kajino, Taro Sekiyama
Hidden units can play essential roles in modeling time-series having long-term dependency or on-linearity but make it difficult to learn associated parameters.
no code implementations • 15 Dec 2016 • Takayuki Osogami
A dynamic Boltzmann machine (DyBM) has been proposed as a model of a spiking neural network, and its learning rule of maximizing the log-likelihood of given time-series has been shown to exhibit key properties of spike-timing dependent plasticity (STDP), which had been postulated and experimentally confirmed in the field of neuroscience as a learning rule that refines the Hebbian rule.
no code implementations • 22 Sep 2016 • Sakyasingha Dasgupta, Takayuki Yoshizumi, Takayuki Osogami
We introduce Delay Pruning, a simple yet powerful technique to regularize dynamic Boltzmann machines (DyBM).
no code implementations • 29 Sep 2015 • Takayuki Osogami, Makoto Otsuka
We propose a particularly structured Boltzmann machine, which we refer to as a dynamic Boltzmann machine (DyBM), as a stochastic model of a multi-dimensional time-series.
no code implementations • NeurIPS 2014 • Takayuki Osogami, Makoto Otsuka
We extend the multinomial logit model to represent some of the empirical phenomena that are frequently observed in the choices made by humans.
no code implementations • NeurIPS 2013 • Tetsuro Morimura, Takayuki Osogami, Tsuyoshi Ide
The Markov chain is a convenient tool to represent the dynamics of complex systems such as traffic and social systems, where probabilistic transition takes place between internal states.
no code implementations • NeurIPS 2012 • Takayuki Osogami
We also show that a risk-sensitive MDP of minimizing an iterated risk measure that is composed of certain coherent risk measures is equivalent to a robust MDP of minimizing the worst-case expectation when the possible deviations of uncertain parameters from their nominal values are characterized with a concave function.