English
Related papers

Related papers: Rank Ordered Autoencoders

200 papers

Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in foundation models by disentangling features into a sparse set of concepts. However, identifying the optimal level of sparsity for…

Machine Learning · Computer Science 2026-04-17 Dongsheng Wang , Jinsen Zhang , Dawei Su , Hui Huang

Bi-linear feature learning models, like the gated autoencoder, were proposed as a way to model relationships between frames in a video. By minimizing reconstruction error of one frame, given the previous frame, these models learn "mapping…

Machine Learning · Computer Science 2014-02-12 Vincent Michalski , Roland Memisevic , Kishore Konda

We present an algorithm to learn the relevant latent variables of a large-scale discretized physical system and predict its time evolution using thermodynamically-consistent deep neural networks. Our method relies on sparse autoencoders,…

Computational Engineering, Finance, and Science · Computer Science 2021-03-25 Quercus Hernandez , Alberto Badias , David Gonzalez , Francisco Chinesta , Elias Cueto

Autoencoders have long been considered a nonlinear extension of Principal Component Analysis (PCA). Prior studies have demonstrated that linear autoencoders (LAEs) can recover the ordered, axis-aligned principal components of PCA by…

Machine Learning · Computer Science 2026-01-28 Qipeng Zhan , Zhuoping Zhou , Zexuan Wang , Li Shen

Generative processes in biology and other fields often produce data that can be regarded as resulting from a composition of basic features. Here we present an unsupervised method based on autoencoders for inferring these basic features of…

Quantitative Methods · Quantitative Biology 2019-10-04 Matteo Negri , Davide Bergamini , Carlo Baldassi , Riccardo Zecchina , Christoph Feinauer

Sparsity in the structure of Neural Networks can lead to less energy consumption, less memory usage, faster computation times on convenient hardware, and automated machine learning. If sparsity gives rise to certain kinds of structure, it…

Machine Learning · Computer Science 2021-07-28 Julian Stier , Harshil Darji , Michael Granitzer

We present a spike-based unsupervised regenerative learning scheme to train Spiking Deep Networks (SpikeCNN) for object recognition problems using biologically realistic leaky integrate-and-fire neurons. The training methodology is based on…

Neural and Evolutionary Computing · Computer Science 2016-02-05 Priyadarshini Panda , Kaushik Roy

One of the roadblocks to a better understanding of neural networks' internals is \textit{polysemanticity}, where neurons appear to activate in multiple, semantically distinct contexts. Polysemanticity prevents us from identifying concise,…

Machine Learning · Computer Science 2023-10-05 Hoagy Cunningham , Aidan Ewart , Logan Riggs , Robert Huben , Lee Sharkey

Reduced-order models are central to motion planning and control of quadruped robots, yet existing templates are often hand-crafted for a specific locomotion modality. This motivates the need for automatic methods that extract task-specific,…

Robotics · Computer Science 2026-01-14 Gioele Buriani , Jingyue Liu , Maximilian Stölzle , Cosimo Della Santina , Jiatao Ding

We demonstrate a new deep learning autoencoder network, trained by a nonnegativity constraint algorithm (NCAE), that learns features which show part-based representation of data. The learning algorithm is based on constraining negative…

Machine Learning · Computer Science 2016-01-13 Ehsan Hosseini-Asl , Jacek M. Zurada , Olfa Nasraoui

We give an algorithm that learns a representation of data through compression. The algorithm 1) predicts bits sequentially from those previously seen and 2) has a structure and a number of computations similar to an autoencoder. The…

Computer Vision and Pattern Recognition · Computer Science 2011-08-05 Karol Gregor , Yann LeCun

Research in Curriculum Learning has shown better performance on the task by optimizing the sequence of the training data. Recent works have focused on using complex reinforcement learning techniques to find the optimal data ordering…

Machine Learning · Computer Science 2022-11-10 Dipankar Sarkar , Mukur Gupta

Reconstruction-based methods play an important role in unsupervised anomaly detection in images. Ideally, we expect a perfect reconstruction for normal samples and poor reconstruction for abnormal samples. Since the generalizability of deep…

Computer Vision and Pattern Recognition · Computer Science 2021-07-29 Jinlei Hou , Yingying Zhang , Qiaoyong Zhong , Di Xie , Shiliang Pu , Hong Zhou

Large occlusions result in a significant decline in image classification accuracy. During inference, diverse types of unseen occlusions introduce out-of-distribution data to the classification model, leading to accuracy dropping as low as…

Computer Vision and Pattern Recognition · Computer Science 2024-02-13 Ketan Kotwal , Tanay Deshmukh , Preeti Gopal

Regularized training of an autoencoder typically results in hidden unit biases that take on large negative values. We show that negative biases are a natural result of using a hidden layer whose responsibility is to both represent the input…

Machine Learning · Statistics 2015-04-09 Kishore Konda , Roland Memisevic , David Krueger

We develop a novel probabilistic generative model based on the variational autoencoder approach. Notable aspects of our architecture are: a novel way of specifying the latent variables prior, and the introduction of an ordinality enforcing…

Machine Learning · Statistics 2018-12-20 Joel Jaskari , Jyri J. Kivinen

Autoencoding is a popular method in representation learning. Conventional autoencoders employ symmetric encoding-decoding procedures and a simple Euclidean latent space to detect hidden low-dimensional structures in an unsupervised way.…

Machine Learning · Computer Science 2024-10-07 Stefan C. Schonsheck , Scott Mahan , Timo Klock , Alexander Cloninger , Rongjie Lai

Principal component analysis, dictionary learning, and auto-encoders are all unsupervised methods for learning representations from a large amount of training data. In all these methods, the higher the dimensions of the input data, the…

Machine Learning · Computer Science 2019-08-27 Thomas Chang , Bahareh Tolooshams , Demba Ba

(This paper was written in November 2011 and never published. It is posted on arXiv.org in its original form in June 2016). Many recent object recognition systems have proposed using a two phase training procedure to learn sparse…

Computer Vision and Pattern Recognition · Computer Science 2016-06-07 Kevin Jarrett , Koray Kvukcuoglu , Karol Gregor , Yann LeCun

Dimension of the encoder output (i.e., the code layer) in an autoencoder is a key hyper-parameter for representing the input data in a proper space. This dimension must be carefully selected in order to guarantee the desired reconstruction…

Machine Learning · Computer Science 2021-02-02 Pedram Fekri , Ali Akbar Safavi , Mehrdad Hosseini Zadeh , Peyman Setoodeh