Anthill Inside 2017

On theory and concepts in Machine Learning, Deep Learning and Artificial Intelligence. Formerly Deep Learning Conf.

About AnthillInside:

In 2016, The Fifth Elephant branched into a separate conference on Deep Learning. Anthill Inside is the new avataar of the Deep Learning conference.
Anthill Inside attempts to bridge the gap bringing theoretical advances closer to functioning reality. Proposals are invited for full length talks, crisp talks and poster/demo sessions in the area of ML+DL. The talks need to focus on the techniques used, and may be presented independent of the domain wherein they are applied.
We also invite talks on novel applications of ML+DL, and methods of realising the same in hardware/software.
Case studies of how DL and ML have been applied in different domains will continue to be discussed at The Fifth Elephant.

https://anthillinside.in/2017/

Topics: we are looking for talks covering the following:

  • Machine Learning with end-to-end application
  • Deep Learning
  • Artificial Intelligence
  • Hardware / software implementations of advanced Machine Learning and Deep Learning
  • IoT and Deep Learning
  • Operations research and Machine Learning

Format:

Anthill Inside is a two-track conference:

  • Talks in the main auditorium and hall 2.
  • Birds of Feather (BOF) sessions in expo area.

We are inviting proposals for:

  • Full-length 40-minute talks.
  • Crisp 15-minute how-to talks or introduction to a new technology.
  • Sponsored sessions, of 15 minutes and 40 minutes duration (limited slots available; subject to editorial scrutiny and approval).
  • Hands-on workshop sessions of 3 and 6 hour duration where participants follow instructors on their laptops.
  • Birds of Feather (BOF) sessions.

You must submit the following details along with your proposal, or within 10 days of submission:

  1. Draft slides, mind map or a textual description detailing the structure and content of your talk.
  2. Link to a self-record, two-minute preview video, where you explain what your talk is about, and the key takeaways for participants. This preview video helps conference editors understand the lucidity of your thoughts and how invested you are in presenting insights beyond your use case. Please note that the preview video should be submitted irrespective of whether you have spoken at past editions of The Fifth Elephant or last year at Deep Learning.
  3. If you submit a workshop proposal, you must specify the target audience for your workshop; duration; number of participants you can accommodate; pre-requisites for the workshop; link to GitHub repositories and documents showing the full workshop plan.

Selection Process:

  1. Proposals will be filtered and shortlisted by an Editorial Panel.
  2. Proposers, editors and community members must respond to comments as openly as possible so that the selection processs is transparent.
  3. Proposers are also encouraged to vote and comment on other proposals submitted here.

We expect you to submit an outline of your proposed talk, either in the form of a mind map or a text document or draft slides within two weeks of submitting your proposal to start evaluating your proposal.

Selection Process Flowchart

You can check back on this page for the status of your proposal. We will notify you if we either move your proposal to the next round or if we reject it. Selected speakers must participate in one or two rounds of rehearsals before the conference. This is mandatory and helps you to prepare well for the conference.

A speaker is NOT confirmed a slot unless we explicitly mention so in an email or over any other medium of communication.

There is only one speaker per session. Entry is free for selected speakers.

We might contact you to ask if you’d like to repost your content on the official conference blog.

Travel Grants:

Partial or full grants, covering travel and accomodation are made available to speakers delivering full sessions (40 minutes) and workshops. Grants are limited, and are given in the order of preference to students, women, persons of non-binary genders, and speakers from Asia and Africa.

Commitment to Open Source:

We believe in open source as the binding force of our community. If you are describing a codebase for developers to work with, we’d like for it to be available under a permissive open source licence. If your software is commercially licensed or available under a combination of commercial and restrictive open source licences (such as the various forms of the GPL), you should consider picking up a sponsorship. We recognise that there are valid reasons for commercial licensing, but ask that you support the conference in return for giving you an audience. Your session will be marked on the schedule as a “sponsored session”.

Important Dates:

  • Deadline for submitting proposals: July 10
  • First draft of the coference schedule: July 15
  • Tutorial and workshop announcements: June 30
  • Final conference schedule: July 20
  • Conference date: July 30

Contact:

For more information about speaking proposals, tickets and sponsorships, contact info@hasgeek.com or call +91-7676332020.

Please note, we will not evaluate proposals that do not have a slide deck and a video in them.

Hosted by

Anthill Inside is a forum for conversations about Artificial Intelligence and Deep Learning, including: Tools Techniques Approaches for integrating AI and Deep Learning in products and businesses. Engineering for AI. more

Amar Lalwani

@amar1707

How Deep is Deep Learning?

Submitted Jul 9, 2017

Undoubtedly Deep Learning is a recent significant step towards Artificial General Intelligence because of its sheer ability to learn most complex tasks. Deep Learning has been shown to achieve spectacular results in almost all domains. But as expected, there is always a price to pay for everything, especially for better things. And here the price is the interpretability and simplicity. Moreover, the amount of resources required by deep learning is huge, but that is not much of a concern in today’s era. With such huge promises, deep learning has become the panacea. Is it really true? How deep is Deep Learning? We explore such questions and will discuss some interesting findings and insights when deep learning is applied in education domain (Knowledge Tracing, to be precise).

Deep Learning was introduced in education domain very recently to trace the learner’s knowledge, which is referred to as Deep Knowledge Tracing (DKT). Knowledge Tracing models the process of knowledge acquisition by tracking learner’s progress/knowledge from interaction to interaction and generates a profile of learner’s strengths and weaknesses. DKT model uses a large hidden layer of LSTM units to model the dynamic and temporal nature of learner’s progression. funtoot is a personalised digital tutor which has more than 1 lakh active students across India. We apply Deep Knowledge Tracing on a dataset generated by 6th Grade students on funtoot which has more than 5 million datapoints (In education domain, the dataset of this size is a rare find). We compare it with the standard classic knowledge tracing models called Bayesian Knowledge (BKT) and Performance Factor Analysis (PFA). DKT outperforms BKT with a very good margin but DKT and PFA perform equally well. We analyse and understand the gain which DKT acheives over BKT and identify probable reasons (limitations) as to why BKT lags behind. Classic BKT, when tweaked and enhanced to overcome those limitations performs as good as DKT. Though, DKT being comparable to classic simple algorithms an advantage of ability to discover the relationships and interdepencies (pre-requisites) among skills.

Owing to a big hidden layer of LSTM units, DKT has parameters of the order of few hundred thousands, while the classical models like PFA and BKT have approximately few hundreds of them. Comparing just in the amount of parameters and the complexity of the models, DKT does not have an edge over much simpler models. A way to interpret this result is to appreciate the depth of the underlying domain of the problem. It seems the domain of knowledge tracing is shallow and the powerful deep learning models are unneccessary. We will discuss more about this in the talk.

This talk is based on our work published as “Few hundred parameters outperform few hundred thousand?” in Educational Data Mining Conference, 2017 (EDM2017).

Outline

  • Define and Explain Knowledge Tracing
  • Explain the domain, skills (knowledge components), funtoot platform and the dataset
  • Discuss and Explain Knowledge Tracing Models
    • Deep Knowledge Tracing (model and architecture)
    • DKT Applications: Discovering relationships and interdepencies (pre-requisites)
    • Bayesian Knowledge Tracing
    • Performance Factor Analysis
  • Analysis, comparison and study of these models
  • Discovering Limitations and Enhancements of BKT
  • Discussion on the depth of deep learning and the knowledge tracing domain
  • Conclusion

Speaker bio

Amar Lalwani, Data Scientist @ funtoot, is responsible for research and development of funtoot’s Brain. funtoot is a personalised digital tutor in K-12 space for Math and Science. funtoot is actively used by more than 1 lakh students and more than 130 schools across India.

Amar Lalwani is also pursuing Ph.D. from IIIT-Bangalore in the area of Machine Learning and Artificial Intelligence.

Links

Slides

https://speakerdeck.com/amar073/how-deep-is-deep-learning

Comments

{{ gettext('Login to leave a comment') }}

{{ gettext('Post a comment…') }}
{{ gettext('New comment') }}
{{ formTitle }}

{{ errorMsg }}

{{ gettext('No comments posted yet') }}

Hosted by

Anthill Inside is a forum for conversations about Artificial Intelligence and Deep Learning, including: Tools Techniques Approaches for integrating AI and Deep Learning in products and businesses. Engineering for AI. more