BibSonomy bookmarks for /tag/deeplearning

[1901.03597] CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learning

dleventis — 2026-09-16T16:10:43+02:00

Abstract page for arXiv paper 1901.03597: CT-GAN: Malicious Tampering of 3D Medical Imagery using Deep Learning

Not yet: the third answer in machine intelligence

thebibleofai — 2026-07-16T20:43:36+02:00

The most difficult thing to build into an artificial intelligence is not accuracy. It is restraint.

Advancing regulatory variant effect prediction with AlphaGenome

thebibleofai — 2026-07-12T21:24:10+02:00

Deep learning models that predict functional genomic measurements from DNA sequences are powerful tools for deciphering the genetic regulatory code. Existing methods involve a trade-off between input sequence length and prediction resolution, thereby limiting their modality scope and performance1,2,3,4,5. We present AlphaGenome, a unified DNA sequence model, which takes as input 1 Mb of DNA sequence and predicts thousands of functional genomic tracks up to single-base-pair resolution across diverse modalities. The modalities include gene expression, transcription initiation, chromatin accessibility, histone modifications, transcription factor binding, chromatin contact maps, splice site usage and splice junction coordinates and strength. Trained on human and mouse genomes, AlphaGenome matches or exceeds the strongest available external models in 25 of 26 evaluations of variant effect prediction. The ability of AlphaGenome to simultaneously score variant effects across all modalities accurately recapitulates the mechanisms of clinically relevant variants near the TAL1 oncogene6. To facilitate broader use, we provide tools for making genome track and variant effect predictions from sequence.

Deep Learning Lectures

topel — 2024-04-08T10:05:38+02:00

10-414/714: Deep Learning Systems

Convolution in MATLAB, NumPy, and SciPy | WolfSound

topel — 2023-12-03T23:44:29+01:00

https://thewolfsound.com/convolution-in-matlab-numpy-and-scipy/

atmorep.org

annakrause — 2023-10-25T15:04:40+02:00

https://www.atmorep.org/#presentations

Session 4_Dueben - Session_4_Dueben_0jVR4Vv.pdf

annakrause — 2023-10-25T15:03:02+02:00

https://climate.esa.int/media/documents/Session_4_Dueben_0jVR4Vv.pdf

GitHub - dynamicslab/databook_python: IPython notebooks with demo code intended as a companion to the book "Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control" by Steven L. Brunton and J. Nathan Kutz

topel — 2023-06-16T15:26:08+02:00

IPython notebooks with demo code intended as a companion to the book "Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control" by Steven L. Brunton and J. Nathan Kutz - GitHub - dynamicslab/databook_python: IPython notebooks with demo code intended as a companion to the book "Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control" by Steven L. Brunton and J. Nathan Kutz

Sequence Feature Extraction for Malware Family Analysis via Graph Neural Network

thebibleofai — 2022-09-25T20:19:57+02:00

Malicious software (malware) causes much harm to our devices and life. We are eager to understand the malware behavior and the threat it made. Most of the record files of malware are variable length and text-based files with time stamps, such as event log data and dynamic analysis profiles. Using the time stamps, we can sort such data into sequence-based data for the following analysis. However, dealing with the text-based sequences with variable lengths is difficult. In addition, unlike natural language text data, most sequential data in information security have specific properties and structure, such as loop, repeated call, noise, etc. To deeply analyze the API call sequences with their structure, we use graphs to represent the sequences, which can further investigate the information and structure, such as the Markov model. Therefore, we design and implement an Attention Aware Graph Neural Network (AWGCN) to analyze the API call sequences. Through AWGCN, we can obtain the sequence embeddings to analyze the behavior of the malware. Moreover, the classification experiment result shows that AWGCN outperforms other classifiers in the call-like datasets, and the embedding can further improve the classic model’s performance.

International Conference on Applied Data Science (ICADS '22)

ereidt — 2022-07-24T11:11:38+02:00

Fuzzy Loss functions for GANs, Learning Analytics, Next Generation AI and Sustainability, Deep Learning for Melodic Frameworks Speakers: Prof. Priti S. Sajja, Sardar Patel University, India Prof. Elvira Popescu, University of Craiova, Romania Dr. Celestine Iwendi, University of Bolton, UK Dr. Vishnu S. Pendyala, San Jose State University, USA Date: Tuesday, July 12, 2022

CS 4787 Spring 2021 Principles of Large-Scale Machine Learning

topel — 2022-03-16T14:37:49+01:00

https://www.cs.cornell.edu/courses/cs4787/2021sp/

End to End Machine Learning

topel — 2022-02-14T08:47:18+01:00

https://end-to-end-machine-learning.teachable.com/courses

Deep Learning & Applied AI | DLAI-s2-2020

topel — 2022-01-12T10:32:56+01:00

Teaching material for the course of Deep Learning and Applied AI, 2nd semester 2020, Sapienza University of Rome

BoltzmannEntropy/interviews.ai: It is my belief that you the postgraduate students and job-seekers for whom the book is primarily meant will benefit from reading it; however, it is my hope that even the most experienced researchers will find it fascinating as well.

bshanks — 2022-01-11T11:37:37+01:00

https://github.com/BoltzmannEntropy/interviews.ai

Do Vision Transformers See Like Convolutional Neural Networks? – La Biblia de la IA – The Bible of AI™ Journal

thebibleofai — 2021-12-05T09:05:25+01:00

««Convolutional neural networks (CNNs) have so far been the de-facto model for visual data. Recent work has shown that (Vision) Transformer models (ViT) can achieve comparable or even superior performance on image classification tasks. This raises a central question: how are Vision Transformers solving these tasks? Are they acting like convolutional networks, or learning entirely different visual representations? Analyzing the internal representation structure of ViTs and CNNs on image classification benchmarks, we find striking differences between the two architectures, such as ViT having more uniform representations across all layers. We explore how these differences arise, finding crucial roles played by self-attention, which enables early aggregation of global information, and ViT residual connections, which strongly propagate features from lower to higher layers. We study the ramifications for spatial localization, demonstrating ViTs successfully preserve input spatial information, with noticeable effects from different classification methods. Finally, we study the effect of (pretraining) dataset scale on intermediate features and transfer learning, and conclude with a discussion on connections to new architectures such as the MLP-Mixer.»

The key challenge for machine learning parameterizations of clouds - Stephan Rasp

annakrause — 2021-12-01T09:23:39+01:00

https://raspstephan.github.io/blog/optimization-dichotomy/#

Point-Based Neural Rendering with Per-View Optimization

shuncheng.wu — 2021-11-24T13:48:51+01:00

http://www-sop.inria.fr/reves/Basilic/2021/KPLD21/KopanasPointBasedNeuralRenderingPerViewOptimization.pdf

Deformed Implicit Field: Modeling 3D Shapes With Learned Dense Correspondence

shuncheng.wu — 2021-11-15T19:23:50+01:00

https://openaccess.thecvf.com/content/CVPR2021/papers/Deng_Deformed_Implicit_Field_Modeling_3D_Shapes_With_Learned_Dense_Correspondence_CVPR_2021_paper.pdf

Model-based Decision Making with Imagination for Autonomous Parking

thebibleofai — 2021-10-10T13:08:35+02:00

Autonomous parking technology is a key concept within autonomous driving research. This paper will propose an imaginative autonomous parking algorithm to solve issues concerned with parking. The proposed algorithm consists of three parts: an imaginative model for anticipating results before parking, an improved rapid-exploring random tree (RRT) for planning a feasible trajectory from a given start point to a parking lot, and a path smoothing module for optimizing the efficiency of parking tasks. Our algorithm is based on a real kinematic vehicle model; which makes it more suitable for algorithm application on real autonomous cars. Furthermore, due to the introduction of the imagination mechanism, the processing speed of our algorithm is ten times faster than that of traditional methods, permitting the realization of real-time planning simultaneously. In order to evaluate the algorithm’s effectiveness, we have compared our algorithm with traditional RRT, within three different parking scenarios. Ultimately, results show that our algorithm is more stable than traditional RRT and performs better in terms of efficiency and quality.

Text Preprocessing Methods for Deep Learning - KDnuggets

ereidt — 2021-09-26T22:06:17+02:00

While the preprocessing pipeline we are focusing on in this post is mainly centered around Deep Learning, most of it will also be applicable to conventional machine learning models too.