Uporedite metode
Pregledajte izabrane metode jednu pored druge; redovi koji se razlikuju su istaknuti.
| Генеративни модел заснован на скору× | Дубоко појачавајуће учење× | |
|---|---|---|
| Oblast | Duboko učenje | Duboko učenje |
| Porodica | Machine learning | Machine learning |
| Godina nastanka≠ | 2019 | 2015 |
| Tvorac≠ | Song, Y. & Ermon, S. | Mnih, V. et al. (DQN) |
| Tip≠ | Score-based generative model (SDE framework) | Sequential decision-making (agent–environment interaction) |
| Temeljni izvor≠ | Song, Y. & Ermon, S. (2019). Generative Modeling by Estimating Gradients of the Data Distribution. NeurIPS 32, 11895–11907. link ↗ | Mnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533. DOI ↗ |
| Drugi nazivi≠ | Skor Tabanlı Üretici Model (Score-Based / SDE), score-based diffusion, SDE-based generative model, score SDE | Derin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRL |
| Srodne≠ | 5 | 4 |
| Sažetak≠ | A score-based generative model, introduced by Yang Song and Stefano Ermon in 2019 and generalized to the stochastic differential equation (SDE) framework in 2021, learns the gradient of the data density — the score — rather than predicting noise directly, and uses it to generate new samples. It is the mathematical generalization that unifies diffusion models under a continuous-time formulation. | Deep Reinforcement Learning combines neural networks with reinforcement learning so an agent learns by interacting with an environment, popularised by Mnih and colleagues' 2015 Nature work on human-level Atari control. Instead of learning from a fixed labelled dataset, the agent takes actions, observes rewards, and gradually shapes a policy that maximises long-run return. |
| ScholarGateSkup podataka ↗ |
|
|