MSE for ILSTM algorithm in binary classification. by Asmaa Ahmed Awad (16726315)

“…The ILSTM was then used to build an efficient intrusion detection system for binary and multi-class classification cases. The proposed algorithm has two phases: phase one involves training a conventional LSTM network to get initial weights, and phase two involves using the hybrid swarm algorithms, CBOA and PSO, to optimize the weights of LSTM to improve the accuracy. …”

The flowchart showing the optimization process of the hybrid methods using BEOSA as the base algorithm and SA and FFA as integrated algorithms. by Olaide N. Oyelade (14047002)

Example medication days generated for patients P4 and P6, medication times (red dots), patient’s state—TRS score (blue line) with bounds for the states (red lines) and optimal stat... by Tomasz Gutowski (17200042)

Learning dynamics on training tasks. by Sam Hall-McMaster (10343795)

Simulation of dense parameter pairs and optimal model output. by Yen-Ju Chen (354876)

Results for the Pattern Generation task. by Paolo Muratore (8331585)

Performance comparison of neural UCB strategies based on the basal ganglia model against other UCB algorithms in different bandit tasks. by Yuhao Wang (196321)

An optimization process of the proposed hybrid BEOSA (HBEOSA) combining both SA and FFA methods into BEOSA. by Olaide N. Oyelade (14047002)

Post scan feature estimates and confidence ratings. by Sam Hall-McMaster (10343795)

Decoding results. by Sam Hall-McMaster (10343795)

Subgroup analysis. by Sam Hall-McMaster (10343795)

Behavioral results. by Sam Hall-McMaster (10343795)

“…Rows are grouped into training and test tasks. <b>A</b>, <b>B</b>, <b>F</b>, <b>G</b>: Theoretical predictions are shown for a model-based algorithm on training (A) and test tasks (F), as well as an SF&GPI algorithm on training (B) and test tasks (G). …”

Comparison of city decoders trained on session one and session two data. by Sam Hall-McMaster (10343795)

Validation tests of feature decoding during the associative memory paradigm. by Sam Hall-McMaster (10343795)

An illustration and comparison of the fitness convergence curves for the Large-scale dataset (WaveformEW), medium-scale dataset (Zoo dataset), and Small-scale (Wine dataset) using... by Olaide N. Oyelade (14047002)

An illustration and comparison of the cost convergence curves for the Large-scale dataset (WaveformEW), medium-scale dataset (Zoo dataset), and Small-scale (Wine dataset) using 50... by Olaide N. Oyelade (14047002)

A radar plot illustrating the comparison of the classification accuracy, cost values, and fitness values for the hybrids of BEOSA when applied to some high-dimensional datasets usi... by Olaide N. Oyelade (14047002)

A radar plot illustrating the comparison of the classification accuracy, cost values, and fitness values for the hybrids of BEOSA when applied to some medium-sized dimensional data... by Olaide N. Oyelade (14047002)

A radar plot illustrating the comparison of the classification accuracy, cost values, and fitness values for the hybrids of BEOSA when applied to some small-sized dimensional datas... by Olaide N. Oyelade (14047002)

Large-scale dataset comparative analysis using computation resources. by Olaide N. Oyelade (14047002)