Chen Yu cwhy
| import csv | |
| from collections import Counter | |
| def get_table(m): | |
| invert_counter = {v: i for i, v in Counter(''.join(m)).items()} | |
| digit_table = { | |
| 'e': invert_counter[4], | |
| 'b': invert_counter[6], | |
| 'f': invert_counter[9], | |
| } |
| html{ | |
| font-size: 16px; | |
| width: 100%; | |
| } | |
| table td, table th { overflow-wrap: anywhere; } | |
| .title>a{ | |
| color: black; | |
| font-size: 1.5rem; | |
| font-family: "charter", "Palatino Linotype", "Source Serif Pro", "Georgia", "serif" | |
| } |
| import torch | |
| def cum_softmax(t: torch.Tensor) -> torch.Tensor: | |
| # t shape: ..., sm_d, sm_d is the dim to reduce | |
| tmax = t.cummax(dim=-1)[0].unsqueeze(-2) | |
| denominator = (t.unsqueeze(-1) - tmax).exp() | |
| # shape: ..., sm_d, csm_d | |
| numerator = denominator.sum(dim=-2, keepdim=True) | |
| return numerator / denominator |
| module Style exposing (..) | |
| type CustomColor | |
| = CItem | |
| | CItemHidden | |
| | CUser | |
| | CUserHidden | |
| | Grey | |
| | White | |
We propose to tackle the problem of end-to-end learning for raw waveforms signals by introducing learnable continuous time-frequency atoms. The derivation of these filters is achieved by first, defining a functional space with a given smoothness order and boundary conditions. From this space, we derive the parametric analytical filters. Their differentiability property allows gradient-based optimization. As such, one can equip any Deep Neural Networks (DNNs) with these filters. This enables us to tackle in a front-end fashion a large scale bird detection task based on the freefield1010 dataset
Modern deep transfer learning approaches have mainly focused on learning \emph{generic} feature vectors from one task that are transferable to other tasks, such as word embeddings in language and pretrained convolutional features in vision. However, these approaches usually transfer unary features and largely ignore more structured graphical representations. This work explores the possibility of learning generic latent graphs that capture dependencies between pairs of data units (e.g., words or pixels) from large- scale unlabeled data and transferring the graphs to downstream tasks. Our
In this paper, we suggest a novel data-driven approach to active learning (AL). The key idea is to train a regressor that predicts the expected error reduction for a candidate sample in a particular learning state. By formulating the query selection procedure as a regression problem we are not restricted to working with existing AL heuristics; instead, we learn strategies based on experience from previous AL outcomes. We show that a strategy can be learnt either from simple synthetic 2D datasets or from a subset of domain-specific data. Our method yields strategies that work well on