REVIEW 6 cited by
Dive into Deep Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
This open-source book represents our attempt to make deep learning approachable, teaching readers the concepts, the context, and the code. The entire book is drafted in Jupyter notebooks, seamlessly integrating exposition figures, math, and interactive examples with self-contained code. Our goal is to offer a resource that could (i) be freely available for everyone; (ii) offer sufficient technical depth to provide a starting point on the path to actually becoming an applied machine learning scientist; (iii) include runnable code, showing readers how to solve problems in practice; (iv) allow for rapid updates, both by us and also by the community at large; (v) be complemented by a forum for interactive discussion of technical details and to answer questions.
Forward citations
Cited by 6 Pith papers
-
TOBACO: Topology Optimization via Band-limited Coordinate Networks for Compositionally Graded Alloys
TOBACO maps a composition-gradation manufacturing limit to a neural-network bandwidth via Bernstein's inequality, making the constraint implicit in the design representation.
-
RAMS: Residual-based adversarial-gradient moving sample method for scientific machine learning in solving partial differential equations
Treating training samples as trainable parameters and moving them along the residual's adversarial gradient improves accuracy across PINN and operator learning benchmarks.
-
Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction
A variational reformulation of the MCR2 objective yields a linear-complexity attention operator, ToST, that matches transformer performance without computing pairwise token similarities.
-
HashAttention: Semantic Sparsity for Faster Inference
HashAttention uses learned 32-bit bit-signatures to retrieve the pivotal context tokens for each query, enabling sparse attention with up to 16x token reduction and minimal average quality loss.
-
Federated Testing (FedTest): A New Scheme to Enhance Convergence and Mitigate Adversarial Attacks in Federating Learning
FedTest lets users evaluate each other's models with local data and aggregates models by these scores, claiming faster convergence and better robustness to malicious users.
-
Explaining in Diffusion: Explaining a Classifier Through Hierarchical Semantics with Text-to-Image Diffusion Models
DiffEx explains classifier decisions by using a vision-language model to build a hierarchical semantic corpus and a beam-search algorithm to rank which visual attributes, alone or in combination, most influence classi...
Discussion (0). Continue with ORCID to comment.