Free tools Windows power users keep installed

One-click scans. No signup required.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.

A weighted average ensemble combines predictions from multiple neural networks by multiplying each model’s output by a coefficient and summing the results. For multiclass classification, combine the models’ probability vectors and choose the class with the highest final score. Select the coefficients on held-out validation data, then compare the tuned ensemble with equal averaging and each model alone; a weighted ensemble is not guaranteed to perform better.

What a weighted average ensemble does

Suppose several neural networks solve the same classification task and output probabilities in the same class order. A weighted ensemble assigns each model a coefficient, scales its probability vector by that coefficient, and adds the scaled vectors together. Models with larger coefficients have more influence on the final prediction.

If the coefficients sum to 1, the result is a weighted average. For example, with two models and weights 0.7 and 0.3, the first model contributes 70% of the combined score and the second contributes 30%. The predicted class is the index with the largest combined score.

This is different from Keras sample weights. Sample weights change how much individual examples contribute to training loss; ensemble weights combine predictions from separate models after training. The Keras guide to built-in training methods describes sample weights in the training context.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.
#1 Best Overall
Elebase USB to USB C Adapter for iPhone 18 Pro Max,USBC Car Charger Adapter
  • Read Before You Buy — No Video Output: These adapters support charging and USB 2.0 data transfer, but cannot transmit video signals. Except for standard USB webcams (which use USB data only), they are not compatible with HDMI/DisplayPort cables, video-capable USB-C hubs, or docking stations with video output.
  • Convert USB-A Ports to USB-C: Designed to connect USB-C earphones, cables, flash drives, card readers, and other USB-C accessories to standard USB-A ports. Plug-and-play with no drivers or software required.
  • Aluminum Alloy Housing: Built with a sturdy aluminum alloy shell that aids in heat dissipation and protects against daily wear and scratches. Designed to maintain a stable and secure connection.
  • Compact & Travel-Friendly: The ultra-compact design allows the adapter to stay plugged into your device without blocking adjacent ports or adding bulk, reducing wear and tear on your original USB ports.
  • 12-Month Warranty: Backed by a 12-month manufacturer warranty for peace of mind. Designed to meet strict quality control standards for reliable everyday performance.

Prepare compatible model predictions

Train multiple networks for the same task, then collect their outputs for examples in a validation set that was not used to fit those models. For multiclass classification, each model should return a probability vector for every example. Confirm that all outputs use the same class ordering and compatible shapes before combining them; otherwise, a class score from one model may be added to a different class score from another.

Probability outputs are the usual input for soft voting, but the probabilities should be meaningfully comparable across models. If one model’s outputs are poorly calibrated or systematically more confident than another’s, its scores may have disproportionate influence even before applying explicit weights. Assess this as an implementation caveat rather than assuming that weights alone correct it.

Rank #2
Anker USB-C Hub, 5-in-1 USB Hub for Laptops, 4K HDMI Multiport Adapter
  • 5-in-1 USB-C Hub: Experience comprehensive connectivity featuring a Power Delivery input, two USB-A 2.0 ports, a USB-A 3.0 port, and an HDMI port. (Note: The USB-C power delivery input port is only for connecting an external wall charger to power your laptop and cannot power peripheral devices.)
  • 90W Pass-Through Charging: Achieve optimal charging with 90W pass-through power to your laptop, supported by a total input of 100W, with the hub reserving 10W for operational efficiency. (Note: Wall charger not included.)
  • Quick Data Transfers: Accelerate your productivity with rapid data transfers using a high-speed 5Gbps USB 3.0 port and two 480Mbps USB 2.0 ports.
  • 4K HDMI Display: Enhance your visual experience with a hub capable of delivering 4K resolution at 30Hz in both mirror and extend modes. Please note that this hub is compatible with MacBook (macOS 12 and newer), Windows 10 and 11, ChromeOS, and laptops equipped with DP Alt Mode and Power Delivery. Note: This device is not compatible with Linux.
  • What You Get: Anker USB-C Hub (5-in-1, 4K HDMI), welcome guide, 18-month warranty, and our friendly customer service.

Choose weights on validation data

There is no guaranteed analytical formula for the best coefficients. Jason Brownlee’s tutorial says, “There is no analytical solution to finding the weights (we cannot calculate them); instead, the value for the weights can be estimated using either the training dataset or a holdout validation dataset.” Brownlee also warns that using the same data to fit the member models and the ensemble weights is likely to overfit. For a more reliable estimate, select weights on representative held-out validation data, not on the models’ training examples.

Choose a metric that matches the task, then search for coefficients that perform well on the validation set. Brownlee’s weighted average ensemble tutorial demonstrates a grid search with candidate coefficients from 0.0 to 1.0 in steps of 0.1, normalizes each candidate vector by its L1 norm, evaluates the ensemble, and prints the best result. Those are settings from an illustrative example, not universal defaults.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.
Rank #3
Sale
Anker USB C Hub, 7in1 Multi-Port USB Adapter, 4K@60Hz USBC to HDMI Splitter
  • Sleek 7-in-1 USB-C Hub: Features an HDMI port, two USB-A 3.0 ports, and a USB-C data port, each providing 5Gbps transfer speeds. It also includes a USB-C PD input port for charging up to 100W and dual SD and TF card slots, all in a compact design.
  • Flawless 4K@60Hz Video with HDMI: Delivers exceptional clarity and smoothness with its 4K@60Hz HDMI port, making it ideal for high-definition presentations and entertainment. (Note: Only the HDMI port supports video projection; the USB-C port is for data transfer only.)
  • Double Up on Efficiency: The two USB-A 3.0 ports and a USB-C port support a fast 5Gbps data rate, significantly boosting your transfer speeds and improving productivity.
  • Fast and Reliable 85W Charging: Offers high-capacity, speedy charging for laptops up to 85W, so you spend less time tethered to an outlet and more time being productive.
  • What You Get: Anker USB-C Hub (7-in-1), welcome guide, 18-month warranty, and our friendly customer service.

Exhaustive search becomes expensive as the number of models and candidate values grows: every additional model expands the combinations to evaluate. The tutorial also identifies linear solvers and gradient descent with a unit-sum constraint as alternatives. Whichever approach you use, constrain or regularize the search when appropriate, and treat a small or unrepresentative validation set as a source of uncertainty rather than as definitive evidence of the best weights.

Implement the weighted prediction

For model predictions arranged as an array with shape (models, examples, classes) and weights arranged as (models,), the combination is a weighted sum over the model axis. In NumPy, a tensor contraction expresses that operation directly:

Rank #4
Sale
UGREEN USB to USB C Adapter Combo 4-Pack, 10Gbps USB C Converter Space Gray
  • Dual Converters, Infinite Potential:Includes 2× USB C male to USB A female adapters and 2× USB A male to USB C female adapters. Perfect for a wide range of uses—tablets with Bluetooth keyboards, expand USB ports on macbook, and more. Two different converters for all your daily needs
  • Next-Level 10Gbps & 3A Charging: No more slow 480Mbps, this usb to usb c adapter has a transfer speed of up to 10Gbps, allowing you to do more transferring in less time. This usb adapter fits both USB A and USB C charger, supporting up to 3A fast charging
  • Upgraded Exquisite Craftsmanship: With an aluminum alloy housing and metal connector, the usbc to usb adapter is extremely durable and sturdy. Rigorously tested to withstand more than 10,000 times of plugging and unplugging, ensuring long-lasting performance
  • Broad Compatible: The usb c to usb adapter widely supports all USB C/ USB A devices like laptops, tablets, cellphones, car chargers, and phone chargers. Such as compatible with MacBook Pro/Air 2023/2022, Thunderbolt 4/3 Devices,Apple MagSafe Watch 9/8/7/SE/Ultra, iPad Pro 2022/2021, Samsung Galaxy S23/S20/S10, and iPhone 17/16/15 Pro. Plug and play
  • Please Note: To reach 10Gbps speed, keep the cable under 3.3 ft. For USB A Male to USB C adapters, try flipping the USB C connector. USB C Male to USB A adapters support bidirectional 10Gbps transfer within 3.3 ft
import numpy as np

# predictions: (number_of_models, number_of_examples, number_of_classes)
# weights:     (number_of_models,)
combined_scores = np.tensordot(weights, predictions, axes=(0, 0))
predicted_classes = np.argmax(combined_scores, axis=1)

To make the result a weighted average, normalize nonnegative candidate weights so they sum to 1 before combining. If weights are already normalized, the division is unnecessary. Check that the model axis is the one being contracted and that each model’s class dimension has the same ordering.

In scikit-learn, classifiers that provide predict_proba can use VotingClassifier with soft voting and classifier weights. Its official documentation explains that the classifier probabilities are multiplied by their weights and averaged, and the class with the highest average probability is selected.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.
Best Value
Anker USB C Hub, 5-in-1 USBC to HDMI Splitter with 4K Display
  • 5-in-1 Connectivity: Equipped with a 4K HDMI port, a 5 Gbps USB-C data port, two 5 Gbps USB-A ports, and a USB C 100W PD-IN port. Note: The USB C 100W PD-IN port supports only charging and does not support data transfer devices such as headphones or speakers.
  • Powerful Pass-Through Charging: Supports up to 85W pass-through charging so you can power up your laptop while you use the hub. Note: Pass-through charging requires a charger (not included). Note: To achieve full power for iPad, we recommend using a 45W wall charger.
  • Transfer Files in Seconds: Move files to and from your laptop at speeds of up to 5 Gbps via the USB-C and USB-A data ports. Note: The USB C 5Gbps Data port does not support video output.
  • HD Display: Connect to the HDMI port to stream or mirror content to an external monitor in resolutions of up to 4K@30Hz. Note: The USB-C ports do not support video output.
  • What You Get: Anker 332 USB-C Hub (5-in-1), welcome guide, our worry-free 18-month warranty, and friendly customer service.
Independent reader supportYour contribution helps us test, update, and keep practical guides available for everyone.Support on Ko-Fi

Evaluate the result without tuning on the test set

Compare the tuned ensemble, an equal-weight average, and each component model using the same held-out evaluation split and metric. Keep final test data out of weight selection; otherwise, the score used to tune coefficients is no longer an independent final evaluation. This separation is especially important because searching many coefficient combinations can fit peculiarities of the validation examples.

  • Record the data split and metric used for evaluation.
  • State which model outputs were combined and how their weights were selected.
  • Report results for the tuned ensemble, equal-weight average, and individual models.
  • Account for the cost of evaluating every member at inference time; an ensemble requires predictions from all included models.

A tuned ensemble may beat an equal average, but it may also tie or underperform the strongest member. Report measured results rather than presenting weighting as a guaranteed improvement.

Version and code considerations

Brownlee’s tutorial is dated August 25, 2020. It notes updates from October 2019 for Keras 2.3 and TensorFlow 2.0, and from January 2020 for changes to scikit-learn v0.22. These are historical version notes, not assurances of compatibility with current releases. Check the code and API behavior against the versions installed in your own environment.

Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.

Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.