Related Experiment Video
Updated: Mar 27, 2026
06:09
P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
Published on: September 8, 2023
1.0K
A Block Successive Lower-Bound Maximization Algorithm for the Maximum Pseudo-Likelihood Estimation of Fully Visible
1School of Mathematics and Physics, University of Queensland, St. Lucia, Brisbane Queensland 4072, Australia h.nguyen7@uq.edu.au.
Neural Computation
|January 7, 2016
Summary
We introduce a novel algorithm for training Boltzmann machines using maximum pseudo-likelihood estimation (MPLE). This block successive lower-bound maximization (BSLM) method guarantees convergence and monotonic improvement for fully visible Boltzmann machines (FVBMs).
Area of Science:
- Machine Learning
- Statistical Modeling
- Artificial Intelligence
Background:
- Maximum pseudo-likelihood estimation (MPLE) is favored for training fully visible Boltzmann machines (FVBMs) due to its scalability and statistical advantages.
- Existing MPLE algorithms lack proven convergence or monotonic properties.
Purpose of the Study:
- To present a novel, convergent, and monotonic algorithm for MPLE of FVBMs.
- To establish theoretical guarantees for the proposed estimation method.
Main Methods:
- Development of an algorithm based on the block successive lower-bound maximization (BSLM) principle.
- Mathematical proof of monotonic increase in pseudo-likelihood values.
- Demonstration of convergence to the unique global pseudo-likelihood maximizer.
Main Results:
- The BSLM algorithm ensures monotonic ascent of pseudo-likelihood values.
- The sequence of BSLM estimates is proven to converge to the global optimum.
- A convergence criterion for the related gradient ascent (GA) algorithm is provided.
Conclusions:
- The BSLM algorithm offers a reliable and theoretically sound method for MPLE of FVBMs.
- This work addresses the lack of proven convergence in previous MPLE algorithms.
- The findings contribute to the robust training of Boltzmann machine models.
Related Concept Videos
01:20Maxwell-Boltzmann Distribution: Problem Solving
3.1K
Individual molecules in a gas move in random directions, but a gas containing numerous molecules has a predictable distribution of molecular speeds, which is known as the Maxwell-Boltzmann distribution, f(v).
This distribution function f(v) is defined by saying that the expected number N (v1,v2) of particles with speeds between v1 and v2 is given by
This distribution function f(v) is defined by saying that the expected number N (v1,v2) of particles with speeds between v1 and v2 is given by
3.1K
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
397
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
397
01:24One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation
1.4K
This lesson introduces two critical methods in pharmacokinetics, the Wagner-Nelson and Loo-Riegelman methods, used for estimating the absorption rate constant (ka) for drugs administered via non-intravenous routes. The Wagner-Nelson method relates ka to the plasma concentration derived from the slope of a semilog percent unabsorbed time plot. However, it is limited to drugs with one-compartment kinetics and can be impacted by factors like gastrointestinal motility or enzymatic degradation.
On...
On...
1.4K
01:25Multimachine Stability
622
Multimachine stability analysis is crucial for understanding the dynamics and stability of power systems with multiple synchronous machines. The objective is to solve the swing equations for a network of M machines connected to an N-bus power system.
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
622
01:05Difference from Background: Limit of Detection
8.9K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
The LOD indicates the presence or absence...
8.9K
01:25Adsorption Isotherms II
99
Brunauer, Emmett, and Teller (BET) introduced a theory in 1938 that modified Langmuir's assumptions to explain multilayer physical adsorption. This theory is applicable to Type II isotherms and provides a more realistic picture of adsorption processes. The BET theory assumes a uniform solid surface with localized adsorption sites, where adsorption at one site doesn't affect adsorption at neighboring sites. This theory also allows for the possibility of additional molecules being adsorbed on top...
99