Influence of cultivation temperature on the ligninolytic activity of selected fungal strains

By Iroon Polytechniou. 2006

Subfields: Computational Biology & Bioinformatics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Biology & Bioinformatics

Citations in the corpus

One billion word benchmark for measuring progress in statistical language modeling (2013, neutral): “Since in practice these models are pruned, often quite aggressively, we also illustrate the negative effect of [Stolcke, 1998] entropy pruning on both models, similar to [Chelba et al., 2010].”
Direct Preference Optimization: Your Language Model is Secretly a Reward Model (2023, methodology): “preferences [35], and prior work has found that fine-tuning LMs using PPO on human preferences to provide more effective summaries.”
The Capacity for Moral Self-Correction in Large Language Models (2023, methodology): “Limitations of the Discrimination Experiment We found fewer standard counterfactual or individual fairness evaluations for discrimination in language models, though some do exist [23, 33].”
Transformers as Soft Reasoners over Language (2020, background): “This goal is quite distinct from question-answering as selecting an answer span in a passage, today’s prevailing paradigm, e.g., [ Rajpurkar et al. , 2016 ] .”
A Simple Language Model for Task-Oriented Dialogue (2020, methodology): “Variants of pre-trained, bidirectional Transformers like BERT [11] are often evaluated on classification tasks such as those in the GLUE benchmark [48] or span-based question answering tasks [40].”
Visual Dialog (2016, methodology): “Some recent large-scale datasets in this domain include the 30M Factoid Question-Answer corpus [44], 100K SimpleQuestions dataset [6], DeepMind Q&A dataset [15], the 20 artificial tasks in the bAbI dataset [57], and the SQuAD dataset for reading comprehension [38].”
ParseNet: Looking Wider to See Better (2015, methodology): “Previous research [20] shows that by concatenating feature from the whole image with features on local patches, it is not necessary to apply CRF smoothing afterwards, as the whole image feature already encodes the smoothness information.”
Federated Learning for Ultra-Reliable Low-Latency V2V Communications (2018, background): “EVT asymptotically characterizes the statistics of extreme events by providing analytical models to analyze network traffic, worst-case delays, peak-to-average-power ratios, and ultra-reliable V2V communication in wireless systems [2], [13]–[15].”
Backdooring Convolutional Neural Networks via Targeted Weight Perturbations (2018, background): “The other, more prevalent class of attacks leveraging perturbations that has been studied is referred to as adversarial examples [10, 19, 7, 31, 21, 23, 25, 29].”
Interpretable Recurrent Neural Networks Using Sequential Sparse Recovery (2016, neutral): “The images come from the Caltech-256 dataset [13].”
AutoHAS: Differentiable Hyper-parameter and Architecture Search (2020, background): “1 dataset [39] is a reading comprehension dataset of 107.”
Accelerating Very Deep Convolutional Networks for Classification and Detection (2015, methodology): “[17] present efficient decompositions 124 by separating k × k filters into k × 1 and 1× k filters, 125 which was earlier developed for accelerating generic 126 image filters [22].”
A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning (2017, methodology): “The dynamics parameter network resembles the locally-linear transitions of [16, 33]; see section 6 for an in depth discussion on the differences.”
The offset tree for learning with partial labels (2008, background): “The interactive v ersion has been analyzed under various additional assumptions (7; 13; 17; 18; 20; 22), including payoff s as a linear function of the side information (1; 2).”
A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models (2016, methodology): “Guided cost learning introduces an iterative sample-based m thod for estimatingZ in the MaxEnt IRL formulation, and can scale to high-dimensional stat e and action spaces and nonlinear cost functions [7].”
Interpreting the Latent Space of GANs for Semantic Face Editing (2019, background): “Latent space is treated as Riemannian manifolds by recent work [8, 2, 19].”
Designing an encoder for StyleGAN image manipulation (2021, methodology): “To this end, we follow our inversion method with several existing editing techniques: StyleFlow [3], InterFaceGAN [34], GANSpace [14], and SeFa [35].”
Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacy (2018, background): “Coded computing for such linear computations has also been studied in [11], [22], [27]–[29].”