——————————————————
The abstract:
—————————————————–
Venue: 2222 Coover Hall
Time: 12.10 – 1.00PM Friday, 23 February.
Venue: 2222 Coover Hall
Time: 12.10 – 1.00PM Friday, 23 February.
Abstract:
Deep learning models are very accurate to give good prediction. However, unlike the traditional shallow models, interpreting such model’s performance is very difficult. In this talk, I shall discuss several approaches which people have used for interpreting the models. Also, we shall discuss about application of such methods on different domains such as manufacturing etc.
——————————-
Location: 2222 Coover Hall
Time: 12.00 Noon, Feb. 16th.
Notes: Slides for this Seminar are available here.
Gauri Jagatap from Dr. Hegde’s research group presented the paper “Symmetry-Breaking Convergence Analysis of Certain Two-layered Neural Networks with ReLU nonlinearity”. You can find the paper here: https://openreview.net/forum?id=Hk85q85ee
————————————————-
Abstract:
In this paper, the authors use dynamical system to analyze the nonlinear weight dynamics of two-layered bias-free networks in the form of g(x; w) = \sum_{j=1}^K \sigma(w_j x), where \sigma(.) is ReLU nonlinearity. The input x is assumed to follow Gaussian distribution.
The authors show that for K = 1 (single ReLU), the nonlinear dynamics can be written in close form, and converges to w* with probability at least (1-\epsilon)/2, if random weight initializations of proper standard derivation (1/\sqrt{d}) are used, verifying empirical practice.
For networks with many ReLU nodes (K >= 2), they apply our closed form dynamics and prove that when the teacher parameters w*_j ‘s form an orthonormal basis,
(1) a symmetric weight initialization yields a convergence to a saddle point and
(2) a certain symmetry-breaking weight initialization yields global convergence to w* without local minima.
They claim that this is the first proof that shows global convergence in nonlinear neural network without unrealistic assumptions on the independence of ReLU activations.
————————————————-
Location: 2222 Coover Hall
Invited talk by Dr. Chinmay Hegde of ECpE on:
————————————————-
“The power of gradient descent”
Many of the recent advances in machine learning can be attributed to two reasons: (i) more available data, and (ii) new and efficient optimization algorithms. Curiously, the simplest primitive from numerical analysis — gradient descent — is at the forefront of these newer ML techniques, even though the functions being optimized are often extremely non-smooth and/or non-convex.
In this series of chalk talks, I will discuss some recent theoretical advances that may shed light onto why this is happening and how to properly approach design of new training techniques.
————————————————-
When?
– 12pm to 1pm, Friday, 19th and 26th January
Where?
– 2222, Coover Hall
————————————————
Lecture notes are available here.
After a hiatus of about five months, we’re finally back in action this semester, with a series of exciting talks lined up! Ardhendu Tripathy, a PhD student with Dr. Aditya Ramamoorthy has volunteered to share his experience from his recent internship at MERL. Please find the details below:
—————————————
In the first few minutes I will describe my internship experience with MERL in Summer 2017, followed by a short talk about the work that was done. The basic subject of the internship was privacy-preserving release of datasets. A report about it can be found at https://arxiv.org/abs/1712.
In the talk, I will describe the problem framework and show a tradeoff between privacy and utility in a case of synthetic data. This tradeoff can be closely attained by using adversarial neural networks. Following that I will visualize the performance on a contrived privacy problem on the MNIST dataset.
Thanks and regards,
Ardhendu
Please find the presentation slides accompanying the talk here.
When?
12th January, Friday (tomorrow), 12pm-1pm.
Where?
2222, Coover Hall.
We’re also going to arrange for some refreshments! Join us!
A summary post on major themes and takeaways from NIPS 2017, by Gauri Jagatap: NIPS 2017: Themes and Takeaways (click on post title to open).
You can now find the presentation slides from our seminar series on this page. Thanks to everyone who attended!
With the ILAS 2017 meet going on at Iowa State University, we had the privilege of inviting two young researchers to give a talk to our audience.
Details of the first talk are as follows:
Date: 28 Jul 2017
Time: 2:00 PM – 3:30 PM
Location:
3043 ECpE Building Addition
Speaker: Ju Sun, Postdoctoral Research Fellow at Stanford University
Title: “When Are Nonconvex Optimization Problems Not Scary?”
For more details, check the department website.
Details for the second talk are as follows:
Date: 28 Jul 2017
Time: 3:45 PM – 5:00 PM
Location:
3043 ECpE Building Addition
Speaker: Ludwig Schmidt, PhD student at MIT
Title: Faster Constrained Optimization via Approximate Projections (tentative)
Refreshments (food and coffee) will be provided! Join us!