We lifted 8 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| ml-research/nsfr | canonical | 4 of 8 |
| Function | Status | Where it lives |
|---|---|---|
| load_images_and_labels | Ran | ml-research/nsfr/src/data_clevr.py code served (permissive licence) · get_code("72186777515c4ad9") |
| load_images_and_labels | Ran | ml-research/nsfr/src/data_kandinsky.py code served (permissive licence) · get_code("f4285fd962226132") |
| valuation_to_rel_string | Ran | ml-research/nsfr/src/nsfr_utils.py code served (permissive licence) · get_code("4e9267acb07f8432") |
| valuation_to_string | Ran | ml-research/nsfr/src/nsfr_utils.py code served (permissive licence) · get_code("be588a24b1b9d8cb") |
| letterbox | Not yet run | ml-research/nsfr/src/data_kandinsky.py code served (permissive licence) · get_code("db89ca1b27aced79") |
| load_image_clevr | Not yet run | ml-research/nsfr/src/data_clevr.py code served (permissive licence) · get_code("31cd0d76f84177bf") |
| load_image_yolo | Not yet run | ml-research/nsfr/src/data_kandinsky.py code served (permissive licence) · get_code("b8300d8a62602ce8") |
| valuation_to_attr_string | Not yet run | ml-research/nsfr/src/nsfr_utils.py code served (permissive licence) · get_code("c3b79d296ee7933e") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Reasoning is an essential part of human intelligence and thus has been a long-standing goal in artificial intelligence research. With the recent success of deep learning, incorporating reasoning with deep learning systems, i.e., neuro-symbolic AI has become a major field of interest. We propose the Neuro-Symbolic Forward Reasoner (NSFR), a new approach for reasoning tasks taking advantage of differentiable forward-chaining using first-order logic. The key idea is to combine differentiable forward-chaining reasoning with object-centric (deep) learning. Differentiable forward-chaining reasoning computes logical entailments smoothly, i.e., it deduces new facts from given facts and rules in a differentiable manner. The object-centric learning approach factorizes raw inputs into representations in terms of objects. Thus, it allows us to provide a consistent framework to perform the forward-chaining inference from raw inputs. NSFR factorizes the raw inputs into the object-centric representations, converts them into probabilistic ground atoms, and finally performs differentiable forward-chaining inference using weighted rules for inference. Our comprehensive experimental evaluations on object-centric reasoning data sets, 2D Kandinsky patterns and 3D CLEVR-Hans, and a variety of tasks show the effectiveness and advantage of our approach.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2110.09383")
get_code_for_paper("2110.09383")
have("2110.09383")
Connect an agent — have() is free.