Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-0205
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-07-13T21:56:44.371858Z
status: published
lens: g_space
sector: science
headline: Deep forest
dek: Current deep-learning models are mostly built upon neural networks, i.e. multiple layers of parameterized differentiable non-linear modules that can be trained by backpropagation. In this paper, we explore the possibility of building deep models based on non-differentiable modules such as decision trees. After a discussion about the mystery behind deep neural networks, particularly by contrasting them with shallow neural networks and traditional machine-learning techniques such as decision trees and boosting mac…
gain_title: Decision-tree ensemble approach called deep forest achieves excellent performance across different domains using the same default setting while requiring fewer hyper-parameters and automatically determining model complexity without gradient-based adjustment or backpropagation.
problem_title: (none)
trace_subject: (none)
gain_reading: Decision-tree ensemble approach called deep forest achieves excellent performance across different domains using the same default setting while requiring fewer hyper-parameters and automatically determining model complexity without gradient-based adjustment or backpropagation.
gain_evidence: with fewer hyper-parameters than deep neural networks | its model complexity can be automatically determined in a data-dependent way | its performance is quite robust to hyper-parameter settings, such that in most cases, even across different data from different domains, it is able to achieve excellent performance by using the same default setting
problem_reading: (none)
problem_evidence: (none)
quick_read: As of the 2018-10-08 publication, researchers proposed deep forest, a decision-tree ensemble that stacks non-differentiable modules in layers to replicate deep learning characteristics without using backpropagation for training.

The approach matters because it suggests deep learning can be achieved outside differentiable neural networks, potentially lowering hyper-parameter tuning burden; uncertainty remains about how broadly the reported robustness generalizes beyond the experiments described and whether theoretical conjecture is fully validated.
limitation: 
tag: Evidence-backed gain
key_points: Proposes deep models built on non-differentiable modules such as decision trees instead of parameterized differentiable non-linear modules trained by backpropagation | Conjectures deep neural network success owes to layer-by-layer processing, in-model feature transformation and sufficient model complexity | Deep forest is a decision-tree ensemble with fewer hyper-parameters than deep neural networks and data-dependent complexity determination
rundown: The authors contrast deep neural networks with shallow networks and traditional techniques such as decision trees and boosting machines to motivate three characteristics for success.

Experiments reported as of 2018-10-08 indicate robustness to hyper-parameter settings, allowing the same default configuration to work across data from different domains.
sources:
- peer_reviewed | National Science Review | https://doi.org/10.1093/nsr/nwy108 | 2018-10-08
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

871dd38e1d7f76a4bc232df87414c8a4d06282ce26113bc0d49ff0053640f1cb

previous

0000000000000000000000000000000000000000000000000000000000000000