CBMM Memos

The new CBMM Memo series achieves the following goals:

  • to share preliminary versions of new results faster than we can by publishing only in traditional journals
  • to fulfill our commitment to NSF
  • to share our work with the broader community
  • to keep track in one place of our joint and cumulative results
  • to create a body of work on the science and technology of intelligence

The CBMM series is posted online via DSpace@MIT and the arXiv.org (which provide a neutral time stamp) and available on our Web site.

Instructions for submitting a new Submission of a CBMM Memo

  • Make sure that the memo describes work that is relevant to the CBMM and is supported at least in part by the CBMM Note: the memo standard acknowledgment says “This work was supported by the Center for Brains, Minds and Machines (CBMM), funded by NSF STC award  CCF – 1231216.” Ask the thrust leader if in doubt.
  • Ask the appropriate CBMM Thrust Leaders to review and approve your memo.
  • Upon Thrust Leader’s approval, contact Kris Brewer, email: brew [a] mit.edu, and cc your Thrust Leader, and request a memo number assignment and the CBMM cover template. Kathleen will send you your memo number and arXiv submission instructions. Please download the appropriate format for your submission of the CBMM Memo Cover Page Template from the Resources page.
  • Login to the CBMM website and click on Add Publication and upload your memo selecting CBMM Memo as the Publication Type.
  • We highly recommend that you upload at least an abstract of your memo to arXiv.org, and preferably the entire Memo, to further disseminate your work.
  • Within a few days of submitting your memo on the Center website, it will be added to the DSpace@MIT collection for you.

Note: The Center does not expect problems with publishing Memos as either pre-prints or post prints. For most major journals, having published a CBMM Memos does not preclude publishing the paper through their journal.

CBMM Memo No.
152
Q. Liao, Ziyin, L., Gan, Y., Cheung, B., Harnett, M., and Poggio, T., “Self-Assembly of a Biologically Plausible Learning Circuit”. 2024.PDF icon CBMM-Memo-152.pdf (1.84 MB)
CBMM Funded
CBMM Memo No.
151
A. Pinto, Rangamani, A., and Poggio, T., “On Generalization Bounds for Neural Networks with Low Rank Layers”. 2024.PDF icon CBMM-Memo-151.pdf (697.31 KB)
CBMM Funded
CBMM Memo No.
150
L. Ziyin, Chuang, I., Galanti, T., and Poggio, T., “Formation of Representations in Neural Networks”. 2024.PDF icon CBMM-Memo-150.pdf (4.03 MB)
CBMM Funded
CBMM Memo No.
149
Y. Gan, Galanti, T., Poggio, T., and Malach, E., “On the Power of Decision Trees in Auto-Regressive Language Modeling”. 2024.PDF icon CBMM-Memo-149.pdf (2.11 MB)
CBMM Funded
CBMM Memo No.
148
Y. Gan and Poggio, T., “For HyperBFs AGOP is a greedy approximation to gradient descent”. 2024.PDF icon CBMM-Memo-148.pdf (1.06 MB)
CBMM Funded
CBMM Memo No.
145
T. Poggio and Fraser, M., “Compositional Sparsity of Learnable Functions”. 2024.PDF icon CBMM-Memo-145.pdf (1.25 MB)
CBMM Funded
CBMM Memo No.
144
M. Xu, Galanti, T., Rangamani, A., Rosasco, L., Pinto, A., and Poggio, T., “The Janus effects of SGD vs GD: high noise and low rank”. 2023.PDF icon Updated with appendix showing empirically that the main results extend to deep nonlinear networks (2.95 MB)PDF icon Small updates...typos... (616.82 KB)
CBMM Funded
CBMM Memo No.
143
Y. Gan and Poggio, T., “A Homogeneous Transformer Architecture”. 2023.PDF icon CBMM Memo 143 v2 (1.1 MB)
CBMM Funded
CBMM Memo No.
142
Y. Xie, Li, Y., and Rangamani, A., “Skip Connections Increase the Capacity of Associative Memories in Variable Binding Mechanisms”. 2023.PDF icon CBMM-Memo-142.pdf (1.64 MB)
CBMM Funded
CBMM Memo No.
141
A. Rangamani, Lindegaard, M., Galanti, T., and Poggio, T., “Feature learning in deep classifiers through Intermediate Neural Collapse”. 2023.PDF icon Feature_Learning_memo.pdf (2.16 MB)
CBMM Funded
CBMM Memo No.
140
T. Galanti, Siegel, Z., Gupte, A., and Poggio, T., “SGD and Weight Decay Provably Induce a Low-Rank Bias in Deep Neural Networks”. 2023.PDF icon Low-rank bias.pdf (2.38 MB)
CBMM Funded
CBMM Memo No.
139
T. Galanti, Xu, M., Galanti, L., and Poggio, T., “Norm-Based Generalization Bounds for Compositionally Sparse Neural Networks”. 2023.PDF icon Norm-based bounds for convnets.pdf (1.2 MB)
CBMM Funded
CBMM Memo No.
138
T. Poggio, “How Deep Sparse Networks Avoid the Curse of Dimensionality: Efficiently Computable Functions are Compositionally Sparse”. 2022.PDF icon v1.0 (984.15 KB)PDF icon v5.7 adding in context learning etc (1.16 MB)
CBMM Funded
CBMM Memo No.
137
A. Rangamani and Xie, Y., “Understanding the Role of Recurrent Connections in Assembly Calculus”. 2022.PDF icon CBMM-Memo-137.pdf (1.49 MB)
CBMM Funded
CBMM Memo No.
136
Y. Han, Poggio, T., and Cheung, B., “System identification of neural systems: If we got it right, would we know?”. 2022.PDF icon CBMM-Memo-136.pdf (1.75 MB)
CBMM Funded
CBMM Memo No.
135
A. Gupte, Banburski, A., and Poggio, T., “PCA as a defense against some adversaries”. 2022.PDF icon CBMM-Memo-135.pdf (2.58 MB)
CBMM Funded
CBMM Memo No.
134
T. Galanti and Poggio, T., “SGD Noise and Implicit Low-Rank Bias in Deep Neural Networks”. 2022.PDF icon Implicit Rank Minimization.pdf (1.76 MB)
CBMM Funded
CBMM Memo No.
133
R. Tejwani, Kuo, Y. - L., Shu, T., Stankovits, B., Gutfreund, D., Tenenbaum, J. B., Katz, B., and Barbu, A., “Incorporating Rich Social Interactions Into MDPs”. 2022.PDF icon CBMM-Memo-133.pdf (1.68 MB)
CBMM Funded
CBMM Memo No.
132
Y. - L. Kuo, Huang, X., Barbu, A., McGill, S. G., Katz, B., Leonard, J. J., and Rosman, G., “Trajectory Prediction with Linguistic Representations”. 2022.PDF icon CBMM-Memo-132.pdf (1.15 MB)
CBMM Funded
CBMM Memo No.
131
C. Conwell, Mayo, D., Buice, M. A., Katz, B., Alvarez, G. A., and Barbu, A., “Neural Regression, Representational Similarity, Model Zoology Neural Taskonomy at Scale in Rodent Visual Cortex”. 2021.PDF icon CBMM-Memo-131.pdf (9.37 MB)
CBMM Funded
CBMM Memo No.
130
R. Tejwani, Kuo, Y. - L., Shu, T., Katz, B., and Barbu, A., “Social Interactions as Recursive MDPs”. 2021.PDF icon CBMM-Memo-130.pdf (1.52 MB)
CBMM Funded
CBMM Memo No.
129
Y. - L. Kuo, Katz, B., and Barbu, A., “Compositional Networks Enable Systematic Generalization for Grounded Language Understanding”. 2021.PDF icon CBMM-Memo-129.pdf (1.2 MB)
CBMM Funded
CBMM Memo No.
128
I. Palmer, Rouditchenko, A., Barbu, A., Katz, B., and Glass, J., “Spoken ObjectNet: A Bias-Controlled Spoken Caption Dataset”. 2021.PDF icon CBMM-Memo-128.pdf (2.91 MB)
CBMM Funded
CBMM Memo No.
127
Y. - L. Kuo, Barbu, A., and Katz, B., “Compositional RL Agents That Follow Language Commands in Temporal Logic”. 2021.PDF icon CBMM-Memo-127.pdf (2.12 MB)
CBMM Funded
CBMM Memo No.
126
C. Ross, Barbu, A., and Katz, B., “Measuring Social Biases in Grounded Vision and Language Embeddings”. 2021.PDF icon CBMM-Memo-126.pdf (1.32 MB)
CBMM Funded
CBMM Memo No.
125
Y. - L. Kuo, Katz, B., and Barbu, A., “Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulas”. 2020.PDF icon CBMM-Memo-125.pdf (2.12 MB)
CBMM Funded
CBMM Memo No.
124
Y. - L. Kuo, Katz, B., and Barbu, A., “Deep compositional robotic planners that follow natural language commands”. 2020.PDF icon CBMM-Memo-124.pdf (1.03 MB)
CBMM Funded
CBMM Memo No.
123
A. Netanyahu, Shu, T., Katz, B., Barbu, A., and Tenenbaum, J. B., “PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception”. 2021.PDF icon CBMM-Memo-123.pdf (3.08 MB)
CBMM Funded
CBMM Memo No.
122
C. Wang, Ross, C., Kuo, Y. - L., Katz, B., and Barbu, A., “Learning a natural-language to LTL executable semantic parser for grounded robotics”. 2020.PDF icon CBMM-Memo-122.pdf (1.03 MB)
CBMM Funded
CBMM Memo No.
121
M. Yamada, D'Amario, V., Takemoto, K., Boix, X., and Sasaki, T., “Transformer Module Networks for Systematic Generalization in Visual Question Answering”. 2022.PDF icon CBMM-Memo-121.pdf (1.06 MB)PDF icon version 2 (3/22/2023) (1.33 MB)
CBMM Funded
CBMM Memo No.
120
S. Ullman, Assif, L., Strugatski, A., Vatashsky, B. - Z., Levi, H., Netanyahu, A., and Yaari, A. Uri, “Image interpretation by iterative bottom-up top- down processing”. 2021.PDF icon CBMM-Memo-120.pdf (2.83 MB)
CBMM Funded
CBMM Memo No.
119
A. Sakai, Sunagawa, T., Madan, S., Suzuki, K., Katoh, T., Kobashi, H., Pfister, H., Sinha, P., Boix, X., and Sasaki, T., “Three approaches to facilitate DNN generalization to objects in out-of-distribution orientations and illuminations”. 2022.PDF icon CBMM-Memo-119.pdf (31.08 MB)
CBMM Funded
CBMM Memo No.
118
T. Poggio, “From Marr’s Vision to the Problem of Human Intelligence”. 2021.PDF icon CBMM-Memo-118.pdf (362.19 KB)
CBMM Funded
CBMM Memo No.
117
M. Xu, Rangamani, A., Banburski, A., Liao, Q., Galanti, T., and Poggio, T., “Dynamics and Neural Collapse in Deep Classifiers trained with the Square Loss”. 2021.PDF icon v1.0 (4.61 MB)PDF icon v1.4corrections to generalization section (5.85 MB)PDF icon v1.7Small edits (22.65 MB)
CBMM Funded
CBMM Memo No.
116
O. Kunhardt, Deza, A., and Poggio, T., “The Effects of Image Distribution and Task on Adversarial Robustness”. 2021.PDF icon CBMM_Memo_116.pdf (5.44 MB)
CBMM Funded
CBMM Memo No.
115
A. Banburski, De La Torre, F., Pant, N., Shastri, I., and Poggio, T., “Distribution of Classification Margins: Are All Data Equal?”. 2021.PDF icon CBMM Memo 115.pdf (9.56 MB)PDF icon arXiv version (23.05 MB)
CBMM Funded
CBMM Memo No.
114
T. Poggio, “From Associative Memories to Powerful Machines”. 2021.PDF icon v1.0 (1.01 MB)PDF icon v1.3Section added August 6 on self attention (3.9 MB)
CBMM Funded
CBMM Memo No.
113
A. Banburski, Gandhi, A., Alford, S., Dandekar, S., Chin, P., and Poggio, T., “Dreaming with ARC”, Learning Meets Combinatorial Algorithms workshop at NeurIPS 2020. 2020.PDF icon CBMM Memo 113.pdf (1019.64 KB)
CBMM Funded
CBMM Memo No.
112
T. Poggio, Liao, Q., and Xu, M., “Implicit dynamic regularization in deep networks”. 2020.PDF icon v1.2 (2.29 MB)PDF icon v.59 Update on rank (2.43 MB)
CBMM Funded
CBMM Memo No.
111
S. Madan, Henry, T., Dozier, J., Ho, H., Bhandari, N., Sasaki, T., Durand, F., Pfister, H., and Boix, X., “On the Capability of Neural Networks to Generalize to Unseen Category-Pose Combinations”. 2020.PDF icon CBMM-Memo-111.pdf (9.76 MB)
CBMM Funded
CBMM Memo No.
110
M. Vuyyuru Reddy, Banburski, A., Pant, N., and Poggio, T., “Biologically Inspired Mechanisms for Adversarial Robustness”. 2020.PDF icon CBMM_Memo_110.pdf (3.14 MB)
CBMM Funded
CBMM Memo No.
109
A. Deza, Liao, Q., Banburski, A., and Poggio, T., “Hierarchically Local Tasks and Deep Convolutional Networks”. 2020.PDF icon CBMM_Memo_109.pdf (2.12 MB)
CBMM Funded
CBMM Memo No.
108
A. Rangamani, Rosasco, L., and Poggio, T., “For interpolating kernel machines, the minimum norm ERM solution is the most stable”. 2020.PDF icon CBMM_Memo_108.pdf (1015.14 KB)PDF icon Better bound (without inequalities!) (1.03 MB)
CBMM Funded
CBMM Memo No.
107
T. Poggio and Cooper, Y., “Loss landscape: SGD has a better view”. 2020.PDF icon CBMM-Memo-107.pdf (1.03 MB)PDF icon Typos and small edits, ver11 (955.08 KB)PDF icon Small edits, corrected Hessian for spurious case (337.19 KB)
CBMM Funded
CBMM Memo No.
106
S. Shalev-Shwartz and Shashua, A., “An Exit Strategy from the Covid-19 Lockdown based on Risk-sensitive Resource Allocation”. 2020.PDF icon CBMM-Memo-106.pdf (431.13 KB)
CBMM Funded
CBMM Memo No.
105
K. M. Villalobos, Štih, V., Ahmadinejad, A., Sundaram, S., Dozier, J., Francl, A., Azevedo, F., Sasaki, T., and Boix, X., “Do Neural Networks for Segmentation Understand Insideness?”. 2020.PDF icon CBMM-Memo-105.pdf (4.63 MB)PDF icon CBMM Memo 105 v2 (July 2, 2020) (3.2 MB)PDF icon CBMM Memo 105 v3 (January 25, 2022) (8.33 MB)
CBMM Funded
CBMM Memo No.
104
S. Shalev-Shwartz and Shashua, A., “Can we Contain Covid-19 without Locking-down the Economy?”. 2020.PDF icon CBMM Memo 104 v4 (Apr. 6, 2020) (418.25 KB)PDF icon CBMM Memo 104 v3 (Apr. 1, 2020) (452.94 KB)PDF icon CBMM Memo 104 v2 (Mar. 28, 2020) (427.39 KB)PDF icon CBMM-Memo-104.pdf (425.12 KB)
CBMM Memo No.
103
T. Poggio, “Stable Foundations for Learning: a framework for learning theory (in both the classical and modern regime).”. 2020.PDF icon Original file (584.54 KB)PDF icon Corrected typos and details of "equivalence" CV stability and expected error for interpolating machines. Added Appendix on SGD.  (905.29 KB)PDF icon Edited Appendix on SGD. (909.19 KB)PDF icon Deleted Appendix. Corrected typos etc (880.27 KB)PDF icon Added result about square loss and min norm (898.03 KB)
CBMM Funded
CBMM Memo No.
102
T. Poggio, Kur, G., and Banburski, A., “Double descent in the condition number”. 2019.PDF icon Fixing typos, clarifying error in y, best approach is crossvalidation (837.18 KB)PDF icon Incorporated footnote in text plus other edits (854.05 KB)PDF icon Deleted previous discussion on kernel regression and deep nets: it will appear, extended, in a separate paper (795.28 KB)PDF icon correcting a bad typo (261.24 KB)PDF icon Deleted plot of condition number of kernel matrix: we cannot get a double descent curve  (769.32 KB)
CBMM Funded
CBMM Memo No.
101
H. Sanders, Wilson, M. A., and Gershman, S. J., “Hippocampal Remapping as Hidden State Inference”. 2019.PDF icon CBMM-Memo-101.pdf (12.78 MB)
CBMM Funded
CBMM Memo No.
100
T. Poggio, Banburski, A., and Liao, Q., “Theoretical Issues in Deep Networks”. 2019.PDF icon CBMM Memo 100 v1 (1.71 MB)PDF icon CBMM Memo 100 v3 (8/25/2019) (1.31 MB)PDF icon CBMM Memo 100 v4 (11/19/2019) (1008.23 KB)
CBMM Funded
CBMM Memo No.
099
A. Adler, Wax, M., and Pantazis, D., “Brain Signals Localization by Alternating Projections”, arXiv. 2019.PDF icon CBMM-Memo-099.pdf (421.67 KB)
CBMM Funded
CBMM Memo No.
098
H. Mhaskar and Poggio, T., “An analysis of training and generalization errors in shallow and deep networks”. 2019.PDF icon CBMM-Memo-098.pdf (687.36 KB)PDF icon CBMM Memo 098 v4 (08/2019) (2.63 MB)
CBMM Funded
CBMM Memo No.
097
B. Myanganbayar, Mata, C., Dekel, G., Katz, B., Ben-Yosef, G., and Barbu, A., “Partially Occluded Hands: A challenging new dataset for single-image hand pose estimation”. 2018.PDF icon CBMM-Memo-097.pdf (8.53 MB)
CBMM Funded
CBMM Memo No.
096
M. Zhang, Feng, J., Lim, J. Hwee, Zhao, Q., and Kreiman, G., “What am I searching for?”. 2018.PDF icon CBMM-Memo-096.pdf (1.74 MB)
CBMM Funded
CBMM Memo No.
095
K. M. Villalobos, Dozier, J., Stih, V., Francl, A., Azevedo, F., Poggio, T., Sasaki, T., and Boix, X., “Can Deep Neural Networks Do Image Segmentation by Understanding Insideness?”. 2018.PDF icon CBMM-Memo-095.pdf (1.96 MB)
CBMM Funded
CBMM Memo No.
094
G. Ben-Yosef, Kreiman, G., and Ullman, S., “Spatiotemporal interpretation features in the recognition of dynamic images”. 2018.PDF icon CBMM-Memo-094.pdf (1.21 MB)Package icon CBMM-Memo-094-dynamic-figures.zip (1.8 MB)File fig1.ppsx (147.67 KB)File fig2.ppsx (419.72 KB)File fig4.ppsx (673.41 KB)File figS1.ppsx (587.88 KB)File figS2.ppsx (281.56 KB)
CBMM Funded
CBMM Memo No.
093
L. Arend, Han, Y., Schrimpf, M., Bashivan, P., Kar, K., Poggio, T., DiCarlo, J. J., and Boix, X., “Single units in a deep neural network functionally correspond with neurons in the brain: preliminary results”. 2018.PDF icon CBMM-Memo-093.pdf (2.99 MB)
CBMM Funded
CBMM Memo No.
092
W. Xiao, Chen, H., Liao, Q., and Poggio, T., “Biologically-plausible learning algorithms can scale to large datasets”. 2018.PDF icon CBMM-Memo-092.pdf (1.31 MB)
CBMM Funded
CBMM Memo No.
091
Q. Liao, Miranda, B., Hidary, J., and Poggio, T., “Classical generalization bounds are surprisingly tight for Deep Networks”. 2018.PDF icon CBMM-Memo-091.pdf (1.43 MB)PDF icon CBMM-Memo-091-v2.pdf (1.88 MB)
CBMM Funded
CBMM Memo No.
090
A. Banburski, Liao, Q., Miranda, B., Poggio, T., Rosasco, L., Hidary, J., and De La Torre, F., “Theory III: Dynamics and Generalization in Deep Networks”. 2018.PDF icon Original, intermediate versions are available under request (2.67 MB)PDF icon CBMM Memo 90 v12.pdf (4.74 MB)PDF icon Theory_III_ver44.pdf Update Hessian (4.12 MB)PDF icon Theory_III_ver48 (Updated discussion of convergence to max margin) (2.56 MB)PDF icon fixing errors and sharpening some proofs (2.45 MB)
CBMM Funded
CBMM Memo No.
089
G. Ben-Yosef and Ullman, S., “Image interpretation above and below the object level”. 2018.PDF icon CBMM-Memo-089.pdf (2.06 MB)
CBMM Funded
CBMM Memo No.
088
A. Yuille and Liu, C., “Deep Nets: What have they ever done for Vision?”. 2018.PDF icon CBMM-Memo-088.pdf (7.88 MB)
CBMM Funded
CBMM Memo No.
087
J. Wang, Zhang, Z., Xie, C., Zhou, Y., Premachandran, V., Zhu, J., Xie, L., and Yuille, A., “Visual concepts and compositional voting”. 2018.PDF icon CBMM-Memo-087.pdf (3.37 MB)
CBMM Funded
CBMM Memo No.
085
W. Shen, Guo, Y., Wang, Y., Zhao, K., Wang, B., and Yuille, A., “Deep Regression Forests for Age Estimation”. 2018.PDF icon CBMM-Memo-085.pdf (2.2 MB)
CBMM Funded
CBMM Memo No.
084
Z. Zhang, Qiao, S., Xie, C., Shen, W., Wang, B., and Yuille, A., “Single-Shot Object Detection with Enriched Semantics”. 2018.PDF icon CBMM-Memo-084.pdf (1.92 MB)
CBMM Funded
CBMM Memo No.
083
Z. Zhang, Xie, C., Wang, J., Xie, L., and Yuille, A., “DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection under Partial Occlusion”. 2018.PDF icon CBMM-Memo-083.pdf (2.32 MB)
CBMM Funded
CBMM Memo No.
082
Y. - S. Wang, Liu, C., Zeng, X., and Yuille, A., “Scene Graph Parsing as Dependency Parsing”. 2018.PDF icon CBMM-Memo-082.pdf (869 KB)
CBMM Funded
CBMM Memo No.
080
W. Shen, Wang, B., Jiang, Y., Wang, Y., and Yuille, A., “Multi-stage Multi-recursive-input Fully Convolutional Networks for Neuronal Boundary Detection”. 2017.PDF icon CBMM-Memo-080.pdf (2.51 MB)
CBMM Funded
CBMM Memo No.
079
C. Liu, Lin, Z., Shen, X., Yang, J., Lu, X., and Yuille, A., “Recurrent Multimodal Interaction for Referring Image Segmentation”. 2018.PDF icon CBMM-Memo-079.pdf (10.16 MB)
CBMM Funded
CBMM Memo No.
078
J. Wang, Xie, C., Zhang, Z., Zhu, J., Xie, L., and Yuille, A., “Detecting Semantic Parts on Partially Occluded Objects”. 2017.PDF icon CBMM-Memo-078.pdf (1.74 MB)
CBMM Funded
CBMM Memo No.
077
A. Adler and Wax, M., “Constant Modulus Algorithms via Low-Rank Approximation”. 2018.PDF icon CBMM-Memo-077.pdf (795.61 KB)
CBMM Funded
CBMM Memo No.
076
H. Mhaskar and Poggio, T., “An analysis of training and generalization errors in shallow and deep networks”. 2018.PDF icon CBMM-Memo-076.pdf (772.61 KB)PDF icon CBMM-Memo-076v2.pdf (2.67 MB)
CBMM Funded
CBMM Memo No.
073
T. Poggio, Kawaguchi, K., Liao, Q., Miranda, B., Rosasco, L., Boix, X., Hidary, J., and Mhaskar, H., “Theory of Deep Learning III: explaining the non-overfitting puzzle”. 2017.PDF icon CBMM-Memo-073.pdf (2.65 MB)PDF icon CBMM Memo 073 v2 (revised 1/15/2018) (2.81 MB)PDF icon CBMM Memo 073 v3 (revised 1/30/2018) (2.72 MB)PDF icon CBMM Memo 073 v4 (revised 12/30/2018) (575.72 KB)
CBMM Funded
CBMM Memo No.
072
C. Zhang, Liao, Q., Rakhlin, A., Miranda, B., Golowich, N., and Poggio, T., “Theory of Deep Learning IIb: Optimization Properties of SGD”. 2017.PDF icon CBMM-Memo-072.pdf (3.66 MB)
CBMM Funded
CBMM Memo No.
071
F. Cano-Córdoba, Sarma, S., and Subirana, B., “Theory of Intelligence with Forgetting: Mathematical Theorems Explaining Human Universal Forgetting using “Forgetting Neural Networks””. 2017.PDF icon CBMM-Memo-071.pdf (2.54 MB)
CBMM Funded
CBMM Memo No.
070
Q. Liao and Poggio, T., “Object-Oriented Deep Learning”. 2017.PDF icon CBMM-Memo-070.pdf (963.54 KB)
CBMM Funded
CBMM Memo No.
069
A. Volokitin, Roig, G., and Poggio, T., “Do Deep Neural Networks Suffer from Crowding?”. 2017.PDF icon CBMM-Memo-069.pdf (6.47 MB)
CBMM Funded
CBMM Memo No.
068
B. Subirana, Bagiati, A., and Sarma, S., “On the Forgetting of College Academics: at "Ebbinghaus Speed"?”. 2017.PDF icon CBMM Memo 068-On Forgetting - June 18th 2017 v2.pdf (713.7 KB)
CBMM Funded
CBMM Memo No.
067
C. Zhang, Liao, Q., Rakhlin, A., Sridharan, K., Miranda, B., Golowich, N., and Poggio, T., “Musings on Deep Learning: Properties of SGD”. 2017.PDF icon CBMM Memo 067 v2 (revised 7/19/2017) (5.88 MB)PDF icon CBMM Memo 067 v3 (revised 9/15/2017) (5.89 MB)PDF icon CBMM Memo 067 v4 (revised 12/26/2017) (5.57 MB)
CBMM Funded
CBMM Memo No.
066
T. Poggio and Liao, Q., “Theory II: Landscape of the Empirical Risk in Deep Learning”. 2017.PDF icon CBMM Memo 066_1703.09833v2.pdf (5.56 MB)
CBMM Funded
CBMM Memo No.
065
N. Cheney, Schrimpf, M., and Kreiman, G., “On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations”. 2017.PDF icon CBMM-Memo-065.pdf (687.76 KB)
CBMM Related
CBMM Memo No.
064
W. Lotter, Kreiman, G., and Cox, D., “Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning”. 2017.PDF icon CBMM-Memo-064.pdf (3 MB)
CBMM Funded
CBMM Memo No.
063
F. Anselmi, Evangelopoulos, G., Rosasco, L., and Poggio, T., “Symmetry Regularization”. 2017.PDF icon CBMM-Memo-063.pdf (6.1 MB)
CBMM Funded
CBMM Memo No.
062
A. Tacchetti, Voinea, S., and Evangelopoulos, G., “Discriminate-and-Rectify Encoders: Learning from Image Transformation Sets”. 2017.PDF icon CBMM-Memo-062.pdf (9.37 MB)
CBMM Funded
CBMM Memo No.
061
G. Ben-Yosef, Assif, L., and Ullman, S., “Full interpretation of minimal images”. 2017.PDF icon CBMM Memo 061 v.1 (4.64 MB)PDF icon CBMM Memo 061 v.2 (5.41 MB)
CBMM Funded
CBMM Memo No.
060
W. Mlynarski and McDermott, J. H., “Learning Mid-Level Auditory Codes from Natural Sound Statistics”. 2017.PDF icon MlynarskiMcDermott_Memo060.pdf (7.11 MB)
CBMM Funded
CBMM Memo No.
059
D. Harari, Gao, T., Kanwisher, N., Tenenbaum, J. B., and Ullman, S., “Measuring and modeling the perception of natural and unconstrained gaze in humans and machines”. 2016.PDF icon CBMM-Memo-059.pdf (1.71 MB)
CBMM Funded
CBMM Memo No.
058
T. Poggio, Mhaskar, H., Rosasco, L., Miranda, B., and Liao, Q., “Theory I: Why and When Can Deep Networks Avoid the Curse of Dimensionality?”. 2016.PDF icon CBMM-Memo-058v1.pdf (2.42 MB)PDF icon CBMM-Memo-058v5.pdf (2.45 MB)PDF icon CBMM-Memo-058-v6.pdf (2.74 MB)PDF icon Proposition 4 has been deleted (2.75 MB)
CBMM Funded
CBMM Memo No.
057
Q. Liao, Kawaguchi, K., and Poggio, T., “Streaming Normalization: Towards Simpler and More Biologically-plausible Normalizations for Online and Recurrent Learning”. 2016.PDF icon CBMM-Memo-057.pdf (1.27 MB)
CBMM Funded
CBMM Memo No.
056
I. Dasgupta, Schulz, E., and Gershman, S. J., “Where do hypotheses come from?”. 2016.PDF icon CBMM-Memo-056-v2.pdf (733.35 KB)
CBMM Funded
CBMM Memo No.
055
Y. Berzak, Huang, Y., Barbu, A., Korhonen, A., and Katz, B., “Anchoring and Agreement in Syntactic Annotations”. 2016.PDF icon CBMM-Memo-055.pdf (768.54 KB)
CBMM Related
CBMM Memo No.
054
H. Mhaskar and Poggio, T., “Deep vs. shallow networks : An approximation theory perspective”. 2016.PDF icon Original submission, visit the link above for the updated version (960.27 KB)
CBMM Funded
CBMM Memo No.
053
G. Dehaene-Lambertz and Spelke, E. S., “The infancy of the human brain”. 2016.PDF icon CBMM-Memo-053.pdf (1.51 MB)
CBMM Funded
CBMM Memo No.
052
Y. Berzak, Kenney, J., Spadine, C., Wang, J. Xian, Lam, L., Mori, K. Sophie, Garza, S., and Katz, B., “Universal Dependencies for Learner English”. 2016.PDF icon memo-52_rev1.pdf (472.67 KB)
CBMM Funded
CBMM Memo No.
051
Y. Berzak, Barbu, A., Harari, D., Katz, B., and Ullman, S., “Do You See What I Mean? Visual Resolution of Linguistic Ambiguities”. 2016.PDF icon memo-51.pdf (2.74 MB)
CBMM Funded
CBMM Memo No.
050
Y. Berzak, Reichart, R., and Katz, B., “Contrastive Analysis with Predictive Power: Typology Driven Estimation of Grammatical Error Distributions in ESL”. 2016.PDF icon memo-50.pdf (493.74 KB)
CBMM Funded
CBMM Memo No.
049
J. Z. Leibo, Liao, Q., Freiwald, W. A., Anselmi, F., and Poggio, T., “View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation”. 2016.PDF icon faceMirrorSymmetry_memo_ver01.pdf (3.93 MB)
CBMM Funded
CBMM Memo No.
048
E. Schulz, Tenenbaum, J. B., Duvenaud, D., Speekenbrink, M., and Gershman, S. J., “Probing the compositionality of intuitive functions”. 2016.PDF icon CBMM-Memo-048.pdf (815.72 KB)
CBMM Related
CBMM Memo No.
047
Q. Liao and Poggio, T., “Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex”. 2016.PDF icon CBMM Memo No. 047 (1.29 MB)
CBMM Funded
CBMM Memo No.
046
B. M. Lake, Ullman, T., Tenenbaum, J. B., and Gershman, S. J., “Building machines that learn and think like people”. 2016.PDF icon machines_that_think.pdf (3.45 MB)
CBMM Funded
CBMM Memo No.
045
H. Mhaskar, Liao, Q., and Poggio, T., “Learning Functions: When Is Deep Better Than Shallow”. 2016.
CBMM Funded
CBMM Memo No.
044
Y. Luo, Boix, X., Roig, G., Poggio, T., and Zhao, Q., “Foveation-based Mechanisms Alleviate Adversarial Examples”. 2016.PDF icon cbmm_memo_044.pdf (11.48 MB)
CBMM Funded
CBMM Memo No.
043
O. Morère, Veillard, A., Lin, J., Petta, J., Chandrasekhar, V., and Poggio, T., “Group Invariant Deep Representations for Image Instance Retrieval”. 2016.PDF icon CBMM-Memo-043.pdf (2.66 MB)
CBMM Funded
CBMM Memo No.
042
L. Isik, Tacchetti, A., and Poggio, T., “Fast, invariant representation for human action in the visual system”. 2016.PDF icon CBMM Memo 042 (3.03 MB)
CBMM Funded
CBMM Memo No.
041
T. Poggio, Anselmi, F., and Rosasco, L., “I-theory on depth vs width: hierarchical function composition”. 2015.PDF icon cbmm_memo_041.pdf (1.18 MB)
CBMM Funded
CBMM Memo No.
040
W. Lotter, Kreiman, G., and Cox, D., “UNSUPERVISED LEARNING OF VISUAL STRUCTURE USING PREDICTIVE GENERATIVE NETWORKS”. 2015.PDF icon CBMM Memo 040_rev1.pdf (1.92 MB)
CBMM Funded
CBMM Memo No.
039
M. Nickel, Rosasco, L., and Poggio, T., “Holographic Embeddings of Knowledge Graphs”. 2015.PDF icon holographic-embeddings.pdf (677.87 KB)
CBMM Funded
CBMM Memo No.
038
M. Vaziri-Pashkam, “Predicting actions before they occur”. 2015.PDF icon PredictingActions (1.43 MB)File Supplemental Video 1: Experimental set up and task (16.38 MB)File Supplemental Video 2: An example FullVid and CutVid trial clips from experiment 4 (5.47 MB)
CBMM Funded
CBMM Memo No.
037
T. Poggio, Rosasco, L., Shashua, A., Cohen, N., and Anselmi, F., “Notes on Hierarchical Splines, DCLNs and i-theory”. 2015.PDF icon CBMM Memo 037 (1.83 MB)
CBMM Funded
CBMM Memo No.
036
Q. Liao, Leibo, J. Z., and Poggio, T., “How Important is Weight Symmetry in Backpropagation?”. 2015.PDF icon 1510.05067v3.pdf (615.32 KB)
CBMM Funded
CBMM Memo No.
035
F. Anselmi, Rosasco, L., Tan, C., and Poggio, T., “Deep Convolutional Networks are Hierarchical Kernel Machines”. 2015.PDF icon CBMM Memo 035_rev5.pdf (975.65 KB)
CBMM Funded
CBMM Memo No.
034
X. Chen and Yuille, A., “Parsing Occluded People by Flexible Compositions”, Computer Vision and Pattern Recognition (CVPR). 2015.PDF icon CBMM Memo 034.pdf (5.54 MB)
CBMM Funded
CBMM Memo No.
033
J. Mao, Xu, W., Yang, Y., Wang, J., Huang, Z., and Yuille, A., “Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)”. 2015.PDF icon CBMM Memo 033.pdf (839.42 KB)
CBMM Funded
CBMM Memo No.
031
A. Yuille and Mottaghi, R., “Complexity of Representation and Inference in Compositional Models with Part Sharing”. 2015.PDF icon CBMM Memo 031.pdf (1.14 MB)
CBMM Funded
CBMM Memo No.
030
H. Shrobe, Katz, B., and Davis, R., “Towards a Programmer's Apprentice (Again)”. 2015.PDF icon CBMM-memo-030.pdf (294.27 KB)
CBMM Funded
CBMM Memo No.
029
F. Anselmi, Rosasco, L., and Poggio, T., “On Invariance and Selectivity in Representation Learning”. 2015.PDF icon CBMM Memo No. 029 (812.07 KB)
CBMM Funded
CBMM Memo No.
028
M. Nickel, Murphy, K., Tresp, V., and Gabrilovich, E., “A Review of Relational Machine Learning for Knowledge Graphs: From Multi-Relational Link Prediction to Automated Knowledge Graph Construction”. 2015.PDF icon CBMM Memo No. 028 (878.56 KB)
CBMM Funded
CBMM Memo No.
027
S. W. Linderman, Johnson, M. J., Wilson, M. A., and Chen, Z., “A Nonparametric Bayesian Approach to Uncovering Rat Hippocampal Population Codes During Spatial Navigation.”. 2014.PDF icon CBMM-Memo-027.pdf (9.44 MB)
CBMM Funded
CBMM Memo No.
026
F. Anselmi and Poggio, T., “Representation Learning in Sensory Cortex: a theory.”. 2014.PDF icon CBMM-Memo-026_neuron_ver45.pdf (1.35 MB)
CBMM Funded
CBMM Memo No.
025
T. Gao, Harari, D., Tenenbaum, J. B., and Ullman, S., “When Computer Vision Gazes at Cognition.”. 2014.PDF icon CBMM-Memo-025.pdf (3.78 MB)
CBMM Funded
CBMM Memo No.
024
N. Amir, Besold, T. R., Camoriano, R., Erdogan, G., Flynn, T., Gillary, G., Gomez, J., Herbert-Voss, A., Hotan, G., Kadmon, J., Linderman, S. W., Liu, T. T., Marantan, A., Olson, J., Orchard, G., Pal, D. K., Pasquale, G., Sanders, H., Silberer, C., Smith, K. A., de Briton, C. Stein N., Suchow, J. W., Tessler, M. H., Viejo, G., Walker, D., Wehbe, L., Barbu, A., Isik, L., Mackevicius, E., and Meroz, Y., “Abstracts of the 2014 Brains, Minds, and Machines Summer Course”. 2014.PDF icon CBMM-Memo-024.pdf (2.86 MB)
CBMM Funded
CBMM Memo No.
023
Q. Liao, Leibo, J. Z., and Poggio, T., “Unsupervised learning of clutter-resistant visual representations from natural videos.”. 2014.PDF icon 1409.3879v2.pdf (3.64 MB)
CBMM Funded
CBMM Memo No.
022
G. Evangelopoulos, Voinea, S., Zhang, C., Rosasco, L., and Poggio, T., “Learning An Invariant Speech Representation”. 2014.PDF icon CBMM-Memo-022-1406.3884v1.pdf (1.81 MB)
CBMM Funded
CBMM Memo No.
021
C. Tan and Poggio, T., “Neural tuning size is a key factor underlying holistic face processing.”. 2014.PDF icon CBMM-Memo-021-1406.3793.pdf (387.79 KB)
CBMM Funded
CBMM Memo No.
020
R. Mottaghi, Fidler, S., Yuille, A., Urtasun, R., and Parikh, D., “Human-Machine CRFs for Identifying Bottlenecks in Holistic Scene Understanding.”. 2014.PDF icon CBMM-Memo-020.pdf (1.89 MB)
CBMM Related
CBMM Memo No.
019
P. Henry Winston, “The Genesis Story Understanding and Story Telling System A 21st Century Step toward Artificial Intelligence.”. 2014.PDF icon CBMM-Memo-019_StoryWhitePaper.pdf (894.38 KB)
CBMM Funded
CBMM Memo No.
018
W. Lu, Lian, X., and Yuille, A., “Parsing Semantic Parts of Cars Using Graphical Models and Segment Appearance Consistency.”. 2014.PDF icon CBMM-Memo-018_opt.pdf (5.02 MB)
CBMM Funded
CBMM Memo No.
017
T. Poggio, Mutch, J., and Isik, L., “Computational role of eccentricity dependent cortical magnification.”. 2014.PDF icon CBMM-Memo-017.pdf (1.04 MB)
CBMM Funded
CBMM Memo No.
015
X. Chen, Mottaghi, R., Liu, X., Fidler, S., Urtasun, R., and Yuille, A., “Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts.”. 2014.PDF icon CBMM-Memo-015.pdf (974.07 KB)
CBMM Funded
CBMM Memo No.
014
Y. Li, Koch, C., Rehg, J. M., and Yuille, A., “The Secrets of Salient Object Segmentation.”. 2014.PDF icon CBMM-Memo-014.pdf (1.59 MB)
CBMM Funded
CBMM Memo No.
013
C. Wang, Wang, Y., Lin, Z., Yuille, A., and Gao, W., “Robust Estimation of 3D Human Poses from a Single Image.”. 2014.PDF icon CBMM-Memo-013.pdf (510.23 KB)
CBMM Funded
CBMM Memo No.
012
A. Barbu, Barrett, D., Chen, W., Siddharth, N., Xiong, C., Corso, J. J., Fellbaum, C. D., Hanson, C., Hanson, S. José, Helie, S., Malaia, E., Pearlmutter, B. A., Siskind, J. Mark, Talavage, T. Michael, and Wilbur, R. B., “Seeing is Worse than Believing: Reading People’s Minds Better than Computer-Vision Methods Recognize Actions”. 2014.PDF icon CBMM Memo 012.pdf (678.95 KB)
CBMM Funded
CBMM Memo No.
011
A. Barbu, Barrett, D., Chen, W., Siddharth, N., Xiong, C., Corso, J. J., Fellbaum, C. D., Hanson, C., Hanson, S. José, Helie, S., Malaia, E., Pearlmutter, B. A., Siskind, J. Mark, Talavage, T. Michael, and Wilbur, R. B., “The Compositional Nature of Event Representations in the Human Brain”. 2014.PDF icon CBMM Memo 011.pdf (3.95 MB)
CBMM Funded
CBMM Memo No.
010
N. D. Goodman, Tenenbaum, J. B., and Gerstenberg, T., “Concepts in a Probabilistic Language of Thought.”. 2014.PDF icon CBMM-Memo-010.pdf (902.53 KB)
CBMM Funded
CBMM Memo No.
009
H. Tang, Buia, C., Madsen, J., Anderson, W. S., and Kreiman, G., “A role for recurrent processing in object completion: neurophysiological, psychophysical and computational evidence.”. 2014.PDF icon CBMM-Memo-009.pdf (4.21 MB)
CBMM Funded
CBMM Memo No.
008
T. Miconi, Groomes, L., and Kreiman, G., “A normalization model of visual search predicts single trial human fixations in an object search task.”. 2014.PDF icon CBMM-Memo-008.pdf (854.51 KB)
CBMM Funded
CBMM Memo No.
007
Y. Berzak, Reichart, R., and Katz, B., “Reconstructing Native Language Typology from Foreign Language Usage.”. 2014.PDF icon CBMM-Memo-007.pdf (683.75 KB)
CBMM Funded
CBMM Memo No.
006
N. Siddharth, Barbu, A., and Siskind, J. Mark, “Seeing What You’re Told: Sentence-Guided Activity Recognition In Video.”. 2014.PDF icon CBMM-Memo-006.pdf (1.2 MB)
CBMM Funded
CBMM Memo No.
005
J. Singer, Madsen, J., Anderson, W. S., and Kreiman, G., “Sensitivity to Timing and Order in Human Visual Cortex.”. 2014.PDF icon CBMM-Memo-005.pdf (1.12 MB)
CBMM Funded
CBMM Memo No.
004
J. Z. Leibo, Liao, Q., Anselmi, F., and Poggio, T., “The Invariance Hypothesis Implies Domain-Specific Regions in Visual Cortex”. 2014.PDF icon CBMM Memo 004_new.pdf (2.25 MB)
CBMM Funded
CBMM Memo No.
003
Q. Liao, Leibo, J. Z., Mroueh, Y., and Poggio, T., “Can a biologically-plausible hierarchy effectively replace face detection, alignment, and recognition pipelines?”. 2014.PDF icon CBMM-Memo-003.pdf (963.66 KB)
CBMM Funded
CBMM Memo No.
002
C. Zhang, Evangelopoulos, G., Voinea, S., Rosasco, L., and Poggio, T., “A Deep Representation for Invariance And Music Classification”. 2014.PDF icon CBMM-Memo-002.pdf (1.63 MB)
CBMM Funded
CBMM Memo No.
001
F. Anselmi, Leibo, J. Z., Rosasco, L., Mutch, J., Tacchetti, A., and Poggio, T., “Unsupervised learning of invariant representations with low sample complexity: the magic of sensory cortex or a new framework for machine learning?”. 2014.PDF icon CBMM Memo No. 001 (940.36 KB)
CBMM Funded